← Back to Archives
VOLUME 13, ISSUE 3, MARCH 2025
Design of GNRFET based Static Random Access Memory for IoTs in Aeronautical Applications
Nasreen Bano, M. Nizamuddin
AI-POWERED PET HEALTH CHATBOT: REVOLUTIONIZING VETERINARY CARE THROUGH INTELLIGENT SYMPTOM ANALYSIS AND TELEMEDICINE INTEGRATION
Lavanya Mahalakshmi B, Mrs. A. Sathiya Priya
THE FUTURE OF HUMAN-MACHINE COLLABORATION IN WORKPLACES: A THEORETICAL APPROACH
M.NAVEEN1, Mrs. A. SATHIYA PRIYA
VIRTUAL MOUSE USING HAND GESTURE RECOGNITION
Agustin Joseph.I, Ms. A. Sathiya Priya
NATURE’S REMEDY ONLINE STORE: AYURVEDIC PRODUCTS FOR WELLNESS
M. KAVIN, DR. S. SHANTHINI
AI-POWERED VIRTUAL ASSISTANT FOR AN EDUCATION PLATFORM (ACADEMIQ)
PAVITHRA R, VAISHNAVI. N
PREFERENCE-BASED VEHICLE SELECTION INTERFACE IN ONLINE CAB BOOKING
M.SAKTHIGANESH, S.SHANTHINI
SENSOR BASED ANOMALY DETECTION SYSTEM FOR SMART JUNCTIONS
BHARATHKUMAR A, VAISHNAVI. N M.Sc., M.Phil., (Ph.D.),
A COMPARATIVE ANALYSIS OF JACCARD AND COSINE SIMILARITY FOR PLAGIARISM DETECTION
Kanishkaa. S, Santhi. K
DETECTING PRODUCT DEMAND OVER TIME USING MACHINE LEARNING
LOGESHWARAN.S., VAISHNAVI.N.M.Sc.,M.Phil.,(Ph.D),
IoT-Based Electronic Door Opening System Using NodeMCU
NAVEEN S, DR.J.SAVITHA
ENHANCING EMERGENCY RESPONSE THROUGH REAL-TIME ACCIDENT DETECTION AND NOTIFICATION
TANUSHREE T R, Dr.R.PRABA
Unknown Person Identification and Alert system for Blind people using face Recognization
V.Sriharan, Dr.S.Shanthini
Smart Contracts vs. Traditional Contracts: A Comparative Analysis
Selvakumar.M, Mrs. A. Sathiya Priya
Blood Cancer Detection and Classification Using Convolutional Neural Networks
S. Varun, Mrs. A. Sathiya Priya
MUSHROOM CLASSIFICATION A MACHINE LEARNING APPROACH
SWEATHA S, Dr. K. THENMOZHI
SMART FIRE & GAS SAFETY SYSTEM: AN IOT-INTEGRATED SYSTEM WITH BLUETOOTH CONTROL USING LABVIEW
Jeevanathan S, Sachin S, Furkhan Anas H, Shujath Ali Khan M, Gopikrishnan A
SMART CHARGING STATIONS – AN ANDROID APPLICATION
DHUSHYANTH. S, DR. PRABA. R
|DOI: 10.17148/IJIREEICE.2025.13318
FRAUD DETECTION AND ANALYSIS FOR INSURANCE CLAIM USING MACHINE LEARNING
D.MANOJ KUMAR, Dr. K. BANUROOPA
DEEP LEARNING BASED MODEL FOR FAKE REVIEW DETECTION
SHARAN K, DR.J. SAVITHA M.Sc., M.Phil., Ph.D
FUTURE-READY INTERFACES: RESPONSIVE & ADAPTIVE DESIGN
Ms. P. Priyadharshini, Mrs. P. Menaka
Prediction Of Cyber-Attacks Using Machine Learning Algorithms
KAMALANATHANAN S, DR. J. SAVITHA
PAWPREDICT USING YOLO (You Only Look Once) FOR OBJECT DETECTION
Deepika. D.S, Santhi. K
DEFECT TRACKING: SOFTWARE DEFECT TRACKING AND REPORTING SYSTEM
A. NEHA, DR. K. THENMOZHI
Machine learning-Driven Detection of Encrypted VPN Traffic in enterprise networks
Vignesh.M, Dr Shanthini. S
Indian traffic sign detection and recognition using deep learning
Mr. M. Lokesh, Mrs. P. Menaka, M.C.A., M.Phil., (Ph.D.),
MACHINE LEARNING APPROACHES FOR CO2 EMISSION ANALYSIS IN TRANSPORTATION
R. LEELA VARSHINI, DR. K. THENMOZHI
RESCUE WINGS WEB COMPUTING AND ACTIVE SERVICES SUPPORT SYSTEM FOR DISASTER RESCUE
SAI SHANKARI V, Dr. J. SAVITHA M.Sc., M.Phil., Ph.D
The Dark Web: An Examination of the Internet’s Shadowy Areas
Mr. G. Balaji, Mrs. P. Menaka, M.C.A., M.Phil., (Ph.D.,)
DETECTION OF CYBERBULLYING ON SOCIAL MEDIA USING MACHINE LEARNING
S. DHANUSRI, DR. J. SAVITHA
FISHERMEN BORDER ALERT SYSTEM USING IOT
LOGA SABARI M, Dr. R.PRABA
LEVERAGING MACHINE LEARNING ALGORITHM FOR DETECTING PSYCHOLOGICAL INSTABILITY
S. KEERTHANA, DR. K. SANTHI
Secure Application Using Multifactor Authentication
K. Naveen, Dr. K. Santhi
A MODULAR EVENT MANAGEMENT SYSTEM WITH REAL-TIME COLLABORATION AND ONLINE BOOKING FEATURES
Rithanya.P.M, Santhi. K
Sustainable Agriculture Marketplace
Ms. C. Divyabharathi, Dr. K. Banuroopa, M.CA., M.Phil., Ph.D.
AI-Powered Cloud Computing: Transforming the Digital Landscape
Ms. G. Santhiya, Mrs. P. Menaka, M.C.A., M.Phil., (Ph.D.)
Promoting Women’s Safety: A GPS-Enabled Internet of Things Tracking System
Ms. S. Monisha, Dr. J. Savitha, M.Sc., M.Phil., Ph. D
A Machine Learning-based System for Fake Profile Identification
S. DHARSHAN, S. SAKTHI VEL, S.S. KISHORE, DR.K. THENMOZHI
Agri-Trade Platform
Mr. A. Aakash, Dr. S. Shanthini, M.Sc., M.Phil., Ph.D.
WATER PIPELINE LEAKAGE DETECTION USING IOT
SUMETHA R G, Dr. R. PRABA
RAINFALL PREDICTION SYSTEM USING MACHINE LEARNING ALGORITHM
Winmaniraja. B, Santhi. K
THE ROLE OF AI AND MACHINE LEARNING IN THE EVOLUTION OF PLANT SCIENCE
Dr. K. Thenmozhi, Nandika. M, Abishri. S
Enhanced Secure Cloud Storage Using Cryptographic Role-Based Access
DHARUN. R, Dr. SHANTHINI. S
AES Based Image Encryption and Decryption for Secure Data Transfer
R. Sriman, Dr. K. Santhi
Automated LED Notification System for Ambulance Alert in High Density Traffic
Kiruthika. N, Shanthini. S
AN OVERVIEW OF MACHINE LEARNING: KEY CONCEPTS, METHODS, APPLICATIONS, AND THE ROLE OF PROGRAMMING LANGUAGES IN ADVANCING AI
Ms. A. Brundha, Dr.K. Thenmozhi., M.Sc., M.Phil., Ph.D.,
ENHANCING SOLAR PANEL EFFICIENCY WITH IOT AND CLOUD TECHNOLOGIES
Thirumalai Kumar G, Lawrance J, Murshath Basha I, Seetharaman R*
THE IMPACT OF UBRANIZATION ON AGRICULTURE AND FOOD SECURITY
SIVARANJANI S, Dr. K. THENMOZHI
A COMPREHENSIVE WEB DATA EXTRACTION SYSTEM: ARCHITECTURE, IMPLEMENTATION, AND ANALYSIS
RAGUNANTHAN.S, Dr. R. PRABA
REAL-TIME VEHICLE SPEED DETECTION USING PYTHON
MANIKANDAN. V, Dr. R. PRABA
Forecasting Stock Prices using ARIMA algorithm
BAVANEESWAR. K, Mrs. MENAKA.P
STRESS DETECTON BASED ON FACIAL EXPRESSION
T. JAYASREE, DR. K. THENMOZHI
VOICE-TO-SIGN TRANSLATOR FOR EMPOWERING COMMUNICATION WITH DEAF AND MUTE
J.VARSHA, Dr. K BANUROOPA
Car spare parts and service provider Platform
A. B. Bhawin, Mrs. A. Sathiya Priya
GRAPHICAL PASSWORD IMAGE SEGMENTATION: A NOVEL APPROACH TO ENHANCED ONLINE SECURITY
OMPRAKASH T, Dr.R. PRABA
COLLEGE FORUMS WITH ALUMNI BASED ON CONTENT FILTERING
Vishwa.B, Mrs.A.Sathiya Priya
Complaint Registration App for E-Governance
Ms. S. Revathi, Dr. J. Savitha M.Sc., M.Phil., Ph.D.
CNN-BASED IMAGE DETECTOR FOR PLANT LEAF DISEASES CLASSIFICATION
RATHYA.N, Dr. K. THENMOZHI
TURFLINK-THE SPORTS FACILITY BOOKING PLATFORM
Ashok Kumar S, Dr. R. Praba
APP SECURITY ANALYSER: AI BASED FRAUD DETECTION USING SENTIMENT INSIGHT
SIVASAMY P, DR. J. SAVITHA
Analyzing, controlling, and dynamically modeling a standalone wind-diesel power system using a GA-PID controller
Dr. M Sankaraiah, Dr. Sd Munvar Ali, Dr. P Ramesh
Design and Implementation of FPGA controlled Nine Level Inverter
Dr. Sd Munvar Ali, Dr. P Ramesh, M Sankaraiah
A Novel Control Method for Enhancing Stability of Interconnected Three Areas System
V.Pardha Saradhi, K.sudherr, Dr.I.prabhakar reddy
Impact Of Electrical Vehicle Charging Station And Fault Ride Through Capability Under Critical Voltage Conditions
S D S Bhagyamma, J Charishma, S Suresh Reddy
HARMONIC REDUCTION OF POWER QUALITY WITH A FUZZY LOGIC BASED SHUNT ACTIVE POWER FILTER
Dr. S Suresh Reddy, S.D.S Bhagyamma, J Charishma
Power management based on ANFIS controllers in autonomous microgrids
M Sreenivasulu, R Ramprasad, T Mabu subhani
Dynamic Stability Enhancement using PSS and UPFC
K V Thulasiram, Dr. N Usha, P Dhana Selvi
Hybrid Renewable Energy System Control for Maximum Power Extraction and Output Voltage Regulation by Using Fuzzy logic Controller
G Subba Reddy, V Anjaneyulu, N Rammohan
Relationship of Flexibility and Injuries in Sports: A Review
Jai Bhagwan Singh Goun
Design and Implementation of a High-Speed Charging Architecture for Intelligent Solar-Powered Battery Charging and Swapping Stations
Onyeyili T.I, Oranugo C.O, Ugwuanyi Gilbert
Abstract
Design of GNRFET based Static Random Access Memory for IoTs in Aeronautical Applications
Nasreen Bano, M. Nizamuddin
DOI: 10.17148/IJIREEICE.2025.13301
Abstract: In this paper, the Static Noise Margin (SNM) and Power consumption of SRAM at different voltage supply and temperatures of Static Random Access Memory for IoTs utilizing Energy efficient GNRFET Technology is simulated using hspice. Further, the Simulation of various Waveforms of the GNRFET SRAM have been presented. SNM is present in SRAM cell which is effect the stability in read operation of the SRAM cells. SRAM cell stability analysis is a based on Static Noise Margin (SNM) investigation when in read mode.. The SRAM cell SNM during read operations analyzing various alternatives to improve cell stability.. The role of GNRFET improves its power efficiency and speed which play vital role in Aeronautical Engineering for various IoT applications. SNM is 6.7@1V, Average Power is 2.24@1V, SNM Is 2.43@45oC, and Average Power is 1.25@45oC.
Keywords: GNR, GNRFET, Power Consumption, Cell Ratio, CMOS, Pull-up Ratio, SNM), Nano-electronic.
Keywords: GNR, GNRFET, Power Consumption, Cell Ratio, CMOS, Pull-up Ratio, SNM), Nano-electronic.
Abstract
AI-POWERED PET HEALTH CHATBOT: REVOLUTIONIZING VETERINARY CARE THROUGH INTELLIGENT SYMPTOM ANALYSIS AND TELEMEDICINE INTEGRATION
Lavanya Mahalakshmi B, Mrs. A. Sathiya Priya
DOI: 10.17148/IJIREEICE.2025.13302
Abstract: The Pet Health Chatbot is a pioneering AI-powered conversational platform designed to provide pet owners with personalized, expert-backed health advice and care recommendations. By inputting their pet's disease or health issue, users are guided through a comprehensive, symptom-assessing questionnaire to determine the severity of the condition. For mild cases, the chatbot offers tailored remedies and care suggestions, while more severe cases are seamlessly directed towards appointment booking with nearby, partnered veterinary hospitals. Users can effortlessly select a hospital, provide essential pet details, and receive instant confirmation and receipt of their booking. By streamlining the veterinary care process, the chatbot reduces wait times, promotes efficient appointment booking, and enhances overall pet care. This transformative platform revolutionizes the way pet owner access veterinary expertise, providing unparalleled convenience, accessibility, and personalized guidance.
Keywords: AI-Powered Chatbot, Pet Healthcare, Veterinary Telemedicine Disease Prediction, Natural Language Processing (NLP)
Keywords: AI-Powered Chatbot, Pet Healthcare, Veterinary Telemedicine Disease Prediction, Natural Language Processing (NLP)
Abstract
THE FUTURE OF HUMAN-MACHINE COLLABORATION IN WORKPLACES: A THEORETICAL APPROACH
M.NAVEEN1, Mrs. A. SATHIYA PRIYA
DOI: 10.17148/IJIREEICE.2025.13303
Abstract: Human and machine collaboration transforms workplaces with the possibilities of efficiency and accuracy through machinery, as well as human innovation and flexibility. This examines this new technological artistic intelligence, including human and human skills, the theoretical fundamentals of cooperation between people and machines, focusing on robotics. Therefore, this study analyzes the interactions of trust, adaptability and common goals in the integration of human and machine workflows. It also discusses development, innovation and impacts on organizational effectiveness.
Keywords: Human and machine collaboration, innovation, theoretical fundamentals.
Keywords: Human and machine collaboration, innovation, theoretical fundamentals.
Abstract
VIRTUAL MOUSE USING HAND GESTURE RECOGNITION
Agustin Joseph.I, Ms. A. Sathiya Priya
DOI: 10.17148/IJIREEICE.2025.13304
Abstract: The creation of a virtual mouse implemented through hand gestures is a big leap in the field of human computer interaction (HCI), granting a touch free way for people to control other devices. In this paper, we present the design and implementation of a virtual mouse system capable of controlling cursors and accessing GUIs based on performing hand gestures. The system uses computer vision techniques specifically the hand tracking algorithms and uses predefined hand gestures and converts them into mouse movement, click and scroll actions. To use computers without physical input devices, hand gestures are accurately detected using such tools as OpenCV and machine learning models. It provides a robust alternative to traditional input methods, if the touch or physical interaction is impractical, due to its reaction time, robustness in a large number of lighting conditions and ease of use. But in fact this project focuses on gesture recognition and the key challenges such as real time processing, accuracy etc.
Keywords: Hand Gesture Recognition, Hand Tracking Technology, Gesture-Controlled Interface, Human-Computer Interaction (HCI), Real-Time Tracking, Computer Vision, Touchless Interaction, Gesture Recognition Algorithm
Keywords: Hand Gesture Recognition, Hand Tracking Technology, Gesture-Controlled Interface, Human-Computer Interaction (HCI), Real-Time Tracking, Computer Vision, Touchless Interaction, Gesture Recognition Algorithm
Abstract
NATURE’S REMEDY ONLINE STORE: AYURVEDIC PRODUCTS FOR WELLNESS
M. KAVIN, DR. S. SHANTHINI
DOI: 10.17148/IJIREEICE.2025.13305
Abstract: The escalating interest in alternative medical practices, especially Ayurveda, has underscored the necessity for a more streamlined mechanism to recommend Ayurvedic treatments for prevalent ailments. This initiative advocates for the creation of a machine learning-driven platform that proposes Ayurvedic pharmaceuticals predicated on symptomatic presentations and diseases. The objective of this system is to amalgamate traditional Ayurvedic principles with contemporary technological advancements to deliver precise and individualized treatment suggestions. The proposed system employs a machine learning model that has been trained on an extensive dataset encompassing Ayurvedic medicinal flora, their characteristics, and their applications for an array of diseases. Through the analysis of the symptoms submitted by users, the model discerns potential diseases and endorses suitable Ayurvedic pharmaceuticals based on their efficacy in addressing the specific condition. Furthermore, the system integrates patient-centric variables, including age, gender, and medical background, to enhance the personalization of the drug recommendations. The utilization of machine learning algorithms, including classification, clustering, and regression methodologies, empowers the system to forecast the most appropriate Ayurvedic pharmaceuticals for the treatment of a designated disease. The recommendation system is constructed upon a user-centric interface, facilitating users to input their symptoms and acquire instantaneous drug recommendations accompanied by comprehensive elucidations of their therapeutic attributes. This system endeavours to reconcile the divide between traditional Ayurvedic medicine and the requirements of contemporary healthcare by furnishing accurate, evidence-informed, and personalized Ayurvedic pharmaceutical recommendations.
Keywords: Ayurvedic medicine, Herbal remedies, Natural treatment, Holistic healing, Traditional medicine, Home remedies, Plant-based medicine, Herbal formulations.
Keywords: Ayurvedic medicine, Herbal remedies, Natural treatment, Holistic healing, Traditional medicine, Home remedies, Plant-based medicine, Herbal formulations.
Abstract
AI-POWERED VIRTUAL ASSISTANT FOR AN EDUCATION PLATFORM (ACADEMIQ)
PAVITHRA R, VAISHNAVI. N
DOI: 10.17148/IJIREEICE.2025.13306
Abstract: AcademIQ is an AI-powered virtual assistant designed to enhance learning experiences for students and support educators by providing real-time responses to academic queries, generating educational content, offering voice- based explanations, and creating personalized learning pathways. Utilizing Natural Language Processing (NLP), AI- driven content generation, and speech synthesis, AcademIQ improves traditional education by making learning more interactive and accessible. The system includes modules for question answering, content generation, voice explanations, personalized learning, and interactive engagement, ensuring a seamless user experience. AcademIQ is evaluated based on accuracy, adaptability, and user engagement, with future improvements planned for video-based explanations, real- time tutoring, and blockchain-based credentialing. This research contributes to the development of AI-driven educational tools, making learning more efficient and personalized.
Keywords: AI in Education, Virtual Assistant, Machine Learning, Natural Language Processing, Personalized Learning, AI-Powered Tutoring, Smart Educational Systems, Adaptive Learning, AI Content Generation.
Keywords: AI in Education, Virtual Assistant, Machine Learning, Natural Language Processing, Personalized Learning, AI-Powered Tutoring, Smart Educational Systems, Adaptive Learning, AI Content Generation.
Abstract
PREFERENCE-BASED VEHICLE SELECTION INTERFACE IN ONLINE CAB BOOKING
M.SAKTHIGANESH, S.SHANTHINI
DOI: 10.17148/IJIREEICE.2025.13307
Abstract: The evolution of online cab booking services has significantly transformed urban transportation, yet many existing platforms lack the ability to provide personalized vehicle selection based on user preferences. This study introduces an advanced preference-based vehicle selection interface that enhances the online cab booking experience by allowing users to filter vehicles based on factors such as comfort, cost, eco-friendliness, seating capacity, and additional features like Wi-Fi and air conditioning. The proposed system integrates a dynamic filtering mechanism that enables users to make informed decisions by offering real-time vehicle availability, detailed specifications, and an option to select a preferred driver based on gender. The interface is designed to provide a seamless, secure, and efficient booking experience while prioritizing accessibility and sustainability. By leveraging technologies such as HTML5, CSS3, JavaScript for the front end, Node.js for the back end, and MySQL/MongoDB for database management, the platform ensures a robust and scalable system. This research highlights the necessity of customization in online cab booking to improve user satisfaction and address the limitations of existing platforms. Future enhancements may include artificial intelligence-driven recommendations, integration with real-time traffic data for better ride estimations, and further expansion of accessibility features to cater to a broader range of user needs. The preference-based selection model presented in this study has the potential to revolutionize online cab booking services by bridging the gap between user expectations and current industry standards.
Keywords: Online Cab Booking, Vehicle Selection, User Preferences, Personalized Filters, Ride Customization, Real- time Availability, Transportation Efficiency, Eco-friendly Vehicles, Accessibility, AI-driven Recommendations
Keywords: Online Cab Booking, Vehicle Selection, User Preferences, Personalized Filters, Ride Customization, Real- time Availability, Transportation Efficiency, Eco-friendly Vehicles, Accessibility, AI-driven Recommendations
Abstract
SENSOR BASED ANOMALY DETECTION SYSTEM FOR SMART JUNCTIONS
BHARATHKUMAR A, VAISHNAVI. N M.Sc., M.Phil., (Ph.D.),
DOI: 10.17148/IJIREEICE.2025.13308
Abstract: The project “Sensor based anomaly Detection System for Smart Junctions” has been developed using C#.Net as front end and SQL server as backend. The project helps to identify the Burglar movement activities and process from CCTV video footage. In a large video surveillance setup, there can easily be thousands of cameras. Constantly monitoring all this video for suspicious behavior is a very resource-consuming task. In some setups, it is however mission critical that this is done. It could for instance be needed in order for a guard to be able to take action on an incident with as little delay as possible. To limit the resources needed to do this monitoring, it would be helpful if the video surveillance system itself, by analyzing the video, could somehow generate a warning if something suspicious or at least abnormal is happening. For identifying the anomaly, the user needs to monitor the video regularly. In such application the proposed anomaly detection model can be applied to effectively identify and creates alerts about the anomaly. The main purpose of this project Monitoring scheme of anomaly will helps to improve the efficiency of the alert mechanism and also identifying the suspected entry. And its provide Automatic Alert system. This can be implemented to any kind of video monitoring application such as road safety, anolomoly movement monitoring applications. The system need some initial training in order to understand what is normal and what is not. This desktop application can implement high level monitoring places.
Keywords: Road safety, Anomaly, Video Surveillance, Alert System, Sensors, Cameras, Smart Junctions.
Keywords: Road safety, Anomaly, Video Surveillance, Alert System, Sensors, Cameras, Smart Junctions.
Abstract
A COMPARATIVE ANALYSIS OF JACCARD AND COSINE SIMILARITY FOR PLAGIARISM DETECTION
Kanishkaa. S, Santhi. K
DOI: 10.17148/IJIREEICE.2025.13309
Abstract: Plagiarism, the unauthorized use or imitation of another’s work without proper acknowledgment, poses a significant challenge in academia, research, and professional content creation, amplified by the widespread sharing of digital information. Reliable plagiarism detection systems are essential to ensure originality and maintain integrity. This paper investigates two widely used algorithms—Jaccard and Cosine similarity—for their effectiveness in detecting textual similarities. Jaccard similarity excels in identifying exact or near-exact overlaps but struggles with rephrased content, whereas Cosine similarity captures deeper semantic similarities, including paraphrasing, but is computationally more demanding. Preprocessing techniques, such as tokenization, stop word removal, and stemming, are employed to optimize the algorithms’ performance. The research evaluates their strengths, limitations, and computational efficiency through a detailed comparative analysis, offering insights into their suitability for specific applications. The findings emphasize the importance of balancing detection accuracy with computational demands, guiding the selection of appropriate methods for plagiarism detection in various contexts.
Keywords: Plagiarism Detection, Cosine Similarity, Jaccard Similarity, Text Similarity, Text Preprocessing
Keywords: Plagiarism Detection, Cosine Similarity, Jaccard Similarity, Text Similarity, Text Preprocessing
Abstract
DETECTING PRODUCT DEMAND OVER TIME USING MACHINE LEARNING
LOGESHWARAN.S., VAISHNAVI.N.M.Sc.,M.Phil.,(Ph.D),
DOI: 10.17148/IJIREEICE.2025.13310
Abstract: Demand forecasting is essential for supply chain management and inventory control, but complex patterns and big datasets are difficult for standard statistical approaches to handle. In order to improve prediction accuracy, this study suggests a machine learning-based strategy that makes use of models like Random Forest Regressor, Gradient Boosting Regressor, Support Vector Regression, and Neural Networks. Preprocessing of the dataset includes train-test separation, scaling, label encoding, and data cleaning. Model performance is evaluated using evaluation measures like accuracy, precision, and recall, while demand patterns are revealed using visualisations like heatmaps and histograms. Neural networks and ensemble learning are combined to enhance predictions even further.This method offers a scalable and dependable demand forecasting solution by bridging the gap between traditional approaches and contemporary machine learning techniques. Businesses may improve inventory management, lessen stock imbalances, and boost profitability through improved resource utilisation and demand prediction by successfully identifying important influencing elements such product classifications and warehouse locations.
Keywords: Motivation of Machine learning Support Vector Regression, Lasso Regression, Random Forest, Gradient Boosting.
Keywords: Motivation of Machine learning Support Vector Regression, Lasso Regression, Random Forest, Gradient Boosting.
Abstract
IoT-Based Electronic Door Opening System Using NodeMCU
NAVEEN S, DR.J.SAVITHA
DOI: 10.17148/IJIREEICE.2025.13311
Abstract: As the need for smart home automation continues to rise, the incorporation of Internet of Things (IoT) technologies into security systems is now a necessity. This paper discusses the design and development of an IoT-based electronic door-opening system using NodeMCU, a widely used microcontroller. The system is designed to offer secure and remote control of door operations through a web-based application, enabling users to control and monitor door security remotely. Through the integration of NodeMCU and IoT, the system improves conventional door security by facilitating real-time monitoring, access control, and remote control. The system discusses hardware and software components of the system, such as the microcontroller, sensors, and user interface. The paper also explains the system development methodology with major focus areas like connectivity, security protocol, and convenience to the user. The designed IoT-based door-opening system provides a cost-effective, expandable, and human-friendly solution to current security issues with simplicity of use coupled with increased security.
Keywords: IoT, NodeMCU, Smart Door Lock, Home Automation, Access Control.
Keywords: IoT, NodeMCU, Smart Door Lock, Home Automation, Access Control.
Abstract
ENHANCING EMERGENCY RESPONSE THROUGH REAL-TIME ACCIDENT DETECTION AND NOTIFICATION
TANUSHREE T R, Dr.R.PRABA
DOI: 10.17148/IJIREEICE.2025.13312
Abstract: An accident remains, a significant cause of injuries and deaths in almost all parts of the world, particularly when a prompt medical facility is denied, says the report of the Ministry of Road Transport and Highways (https://morth.nic.in/road-accident-in-india). More delays in its recognition and response saturate the headlines with unavoidable and easily controlled accidents. Available accident detection and emergency notification systems fall short of standard procedures due to delayed warnings, lack of customization of emergency contacts, and inapplicability in many unanticipated emergency scenarios.
Therefore, the proposed system intends, differently to provide an effective real-time solution that can automatically detect any kind of accident and dispatch alerts to the relevant custom emergency contacts. The system incorporates cutting-edge sensing technologies, machine learning, and user-centered design into a single innovative approach to offering timely and effective police notification. Such customization enables anyone to populate one's list of emergency contacts, rounding off its capability of a seamless application across various user preferences and circumstances by saving lives and improving outcomes in an accident scenario.
Keywords: Accident detection - emergency notification - real-time solution - machine learning - sensing technologies - user-centered design - emergency contacts - police notification - timely response - injury prevention.
Therefore, the proposed system intends, differently to provide an effective real-time solution that can automatically detect any kind of accident and dispatch alerts to the relevant custom emergency contacts. The system incorporates cutting-edge sensing technologies, machine learning, and user-centered design into a single innovative approach to offering timely and effective police notification. Such customization enables anyone to populate one's list of emergency contacts, rounding off its capability of a seamless application across various user preferences and circumstances by saving lives and improving outcomes in an accident scenario.
Keywords: Accident detection - emergency notification - real-time solution - machine learning - sensing technologies - user-centered design - emergency contacts - police notification - timely response - injury prevention.
Abstract
Unknown Person Identification and Alert system for Blind people using face Recognization
V.Sriharan, Dr.S.Shanthini
DOI: 10.17148/IJIREEICE.2025.13313
Abstract: This project entitled "Unknown Person Identification and Alert system for Blind people using face Recognition " is developed using Python programming language. Security is a very important term because most crimes are taking place in cities rather than in rural areas. So it is compulsory to appoint a watchman or security guards, which is not affordable for everyone. IOT-based security and technological substitutions have easy but much costlier maintenance requirements. The primary goal of this project is to develop a software application that will help identify intruders using Opencv. Computer vision and OpenCV have mitigated this problem through the proposed system. The system can detect and recognize a person based on the data previously provided to it. The proposed system is capable of face detection and reorganization of a person to identify whether the person in the frame is a known person or an intruder. Haar-cascade models are used for detecting human face. This portion of a face is then given for recognition through a model trained on LBPH. The model returns the probability of recognition in the frame for each person. Furthermore, the system can trigger the alarm when it comes to finding any intruder concerning human beings. This can be integrated into any kind of video monitoring like safety to banks, burglar movement monitoring applications, etc. The system will definitely require some kind of initial training to learn what is normal and then an intruder. The development of this system is mainly to make it user-friendly and by that, reduce the amount of manual monitoring work possible.
Keywords: Face Recognition, Computer vision, Haar-cascade, Local Binary Pattern Histogram (LBPH)
Keywords: Face Recognition, Computer vision, Haar-cascade, Local Binary Pattern Histogram (LBPH)
Abstract
Smart Contracts vs. Traditional Contracts: A Comparative Analysis
Selvakumar.M, Mrs. A. Sathiya Priya
DOI: 10.17148/IJIREEICE.2025.13314
Abstract: Smart contracts were made famous in the 2017 ethereum blockchain, automating transactions by inserting terms into code which eliminated the requirement of any middlemen. Execution of these contracts is automated, transparent, and secure. Automated contracts provide potent advantages, such as cost-saving, enhanced security, and increased efficiency, which make them integral to decentralized finance (defi), decentralized apps (dapps), and non- fungible tokens (nfts). Smart contracts exceed mere contracts. They enable interoperability of the blockchain with the internet of things (iot) via application logic contracts (alcs) and decentralized autonomous organizations (daos). Despite such promise, some problems persist, from technical difficulties to loopholes in nascent legal frameworks. This article discusses their mechanisms, uses, and limitations and places emphasis on their social implications and future directions.
Keywords: Blockchain Technology; Smart contract, Traditional Contract Decentralized Systems, smart contract security, Internet of Things (IoT), Security, Pay to public key hash (p2pkh), Multi-signature contracts (multisig), Hash time-lock contracts (htlcs), Discrete log contracts (dlcs) Pay to taproot (p2tr).
Keywords: Blockchain Technology; Smart contract, Traditional Contract Decentralized Systems, smart contract security, Internet of Things (IoT), Security, Pay to public key hash (p2pkh), Multi-signature contracts (multisig), Hash time-lock contracts (htlcs), Discrete log contracts (dlcs) Pay to taproot (p2tr).
Abstract
Blood Cancer Detection and Classification Using Convolutional Neural Networks
S. Varun, Mrs. A. Sathiya Priya
DOI: 10.17148/IJIREEICE.2025.13315
Abstract: Blood cancer detection and classification play a crucial role in early diagnosis and treatment planning. This study proposes a Convolutional Neural Network (CNN)-based approach for the automated detection and classification of blood cancer using Peripheral Blood Smear (PBS) images. The model classifies images into benign and malignant (ALL) categories, further distinguishing between its subtypes: Early Pre-B, Pre-B, and Pro-B. The system is integrated into a web-based application for real-time image analysis. Experimental results demonstrate the effectiveness of CNNs in achieving high classification accuracy, aiding in automated and reliable leukemia diagnosis.
Keywords: Blood Cancer, Acute Lymphoblastic Leukemia, Convolutional Neural Networks, Peripheral Blood Smear, Deep Learning
Keywords: Blood Cancer, Acute Lymphoblastic Leukemia, Convolutional Neural Networks, Peripheral Blood Smear, Deep Learning
Abstract
MUSHROOM CLASSIFICATION A MACHINE LEARNING APPROACH
SWEATHA S, Dr. K. THENMOZHI
DOI: 10.17148/IJIREEICE.2025.13316
Abstract: Accurately identifying edible and toxic mushrooms is essential to preventing foodborne illnesses, as misclassification can lead to severe health risks. Traditional classification methods often depend on expert judgment, which can be subjective, time-consuming, and prone to errors. This study investigates the use of machine learning to automate the classification of mushrooms into edible and poisonous categories. Leveraging the UCI Mushroom Dataset, which includes features such as cap shape, color, gill spacing, and habitat, we evaluate three machine learning models: Decision Trees, Random Forests, and Logistic Regression. The findings demonstrate that these models achieve high accuracy, proving their effectiveness in mushroom classification. To enhance model performance, preprocessing techniques such as feature selection and handling class imbalances are applied. The results highlight the potential of machine learning in improving food safety, assisting foragers, and supporting agricultural applications. Future work could explore deep learning for image-based classification and incorporate environmental factors to refine real-time decision- making systems.
Keywords: Machine Learning, Mushroom Classification, Decision Tree, Random Forest, Logistic Regression.
Keywords: Machine Learning, Mushroom Classification, Decision Tree, Random Forest, Logistic Regression.
Abstract
SMART FIRE & GAS SAFETY SYSTEM: AN IOT-INTEGRATED SYSTEM WITH BLUETOOTH CONTROL USING LABVIEW
Jeevanathan S, Sachin S, Furkhan Anas H, Shujath Ali Khan M, Gopikrishnan A
DOI: 10.17148/IJIREEICE.2025.13317
Abstract: Fire and gas leak incidents pose significant threats to safety in industrial and residential environments. This work presents a real-time fire, gas, and temperature monitoring system designed for early hazard detection and prevention. The system integrates an MQ-5 gas sensor, a single-channel flame sensor, and an LM35 temperature sensor to continuously monitor environmental conditions. In the event of a gas leak or fire detection, an alarm system comprising a buzzer, LED indicators, and an automated sprinkler system is activated to mitigate risks. To enhance system control and accessibility, Bluetooth communication allows users to manually control the sprinkler, buzzer, and LED using a mobile application via predefined commands. Additionally, the system is equipped with IoT-based remote monitoring through Firebase, enabling real-time data storage and analysis. The data transmitted to real time database which includes gas and fire status, temperature readings, and system responses, ensuring remote visibility and decision-making. The system is implemented using MyRIO as the central processing unit, interfacing with LabVIEW for real-time monitoring. The proposed system enhances safety, automation, and monitoring efficiency while providing seamless remote accessibility. Experimental results demonstrate the system’s effectiveness in detecting hazards with high accuracy and rapid response time.
Keywords: Fire detection, Gas monitoring, IoT, MyRIO, Bluetooth communication, LabVIEW.
Keywords: Fire detection, Gas monitoring, IoT, MyRIO, Bluetooth communication, LabVIEW.
Abstract
FRAUD DETECTION AND ANALYSIS FOR INSURANCE CLAIM USING MACHINE LEARNING
D.MANOJ KUMAR, Dr. K. BANUROOPA
DOI: 10.17148/IJIREEICE.2025.13319
Abstract: Insurance claim fraud detection is a serious problem, resulting in heavy financial loss to insurers and impacting policyholder premium levels. The current methods for fraud detection are rule-based and manual inspection- based and are mostly inefficient and error-prone. The use of Machine Learning (ML) methods to enhance the detection and investigation of fraudulent insurance claims is explored in this paper. Employing several ML algorithms, i.e., supervised learning techniques including Random Forests, Support Vector Machines, and neural networks, we illustrate how fraud activity from historical claims data can be discovered and leveraged to predict fraud risk. The article describes the preprocessing of the claims data, feature engineering, model estimation, and validation procedures in the design of successful fraud detection models.
Abstract
HANDWRITTEN CHARACTER ECOGNITION
B.A. SUKESH, Dr. J. SAVITHA
DOI: 10.17148/IJIREEICE.2025.13320
Abstract: The project “Handwritten character recognition system “This application is developed using python as the front-end and my sql as the back-end. Currently, Handwritten character Recognition is a pivotal concern in computer vision. Machine Learning technology makes a machine efficient to perform pattern or text recognition. Handwriting patterns differ according to the speaker it is normally quite difficult to recognize. Main aim of the proposed system is develop automatically recognizing and detecting handwritten character Recognition using Decision tree Machine Learning models. Our proposed system initially began with camera user can able to write character in paper. After that user can able to show the writer character in front of the camera. Camera will the image after capture the image passes to CNN will completely extract information from the capture image. Finally capture information maintain in test data database. Finally proposed system applies Rule-based classifiers which make the class decision depending by using various rules. Finally classification output will show user captures test data whether character or Not.
Abstract
DEEP LEARNING BASED MODEL FOR FAKE REVIEW DETECTION
SHARAN K, DR.J. SAVITHA M.Sc., M.Phil., Ph.D
DOI: 10.17148/IJIREEICE.2025.13321
Abstract: Many individuals look for product reviews before making purchase decisions. They often encounter various reviews online, but it can be difficult for users to determine whether these reviews are authentic or deceptive. Certain review platforms may post favorable reviews created by the manufacturers themselves to manipulate perceptions and generate misleadingly positive feedback for their products. Consequently, users may struggle to discern the authenticity of a review. To address the issue of identifying fake reviews online, a Deep Learning Based Model for Fake Review Detection has been developed. This system aims to detect fraudulent reviews by tracking the IP addresses of users along with their purchasing behavior. Users can log into the system with their user ID and password, browse different products, and submit reviews. To assess whether a review is authentic or fake, the system checks the user's IP address. If the system detects multiple fake reviews originating from the same IP address, it will notify the admin to delete those reviews from the system. The system adopts data mining techniques. This solution assists users in finding accurate reviews about products.
To tackle this challenge, we suggest a model based on deep learning for identifying fraudulent reviews in e-commerce websites and service-based sectors. This model utilizes natural language processing (NLP) methods to examine text data and uncover patterns that suggest the presence of fake reviews. By employing sophisticated deep learning frameworks, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the system is capable of discerning subtle linguistic indicators, sentiment irregularities, and behavioural trends that set genuine reviews apart from fake ones. Furthermore, we make use of pre-trained word embeddings like Word2Vec or Glove to capture the semantic connections between words, thus improving the model's capability to comprehend context and intent. The model is developed using a substantial dataset of labelled reviews, including both positive and negative feedback, to ensure its robustness. Through thorough evaluation, the deep learning model achieves a high level of accuracy in categorizing fake reviews, providing an effective means to bolster trust and reliability in online review systems. This strategy could be integrated into current platforms, enabling real-time detection of fake reviews and protecting both users and businesses from deceptive practices.
Keywords: Fake review detection Deep learning Convolutional Neural Networks (CNNs)
To tackle this challenge, we suggest a model based on deep learning for identifying fraudulent reviews in e-commerce websites and service-based sectors. This model utilizes natural language processing (NLP) methods to examine text data and uncover patterns that suggest the presence of fake reviews. By employing sophisticated deep learning frameworks, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the system is capable of discerning subtle linguistic indicators, sentiment irregularities, and behavioural trends that set genuine reviews apart from fake ones. Furthermore, we make use of pre-trained word embeddings like Word2Vec or Glove to capture the semantic connections between words, thus improving the model's capability to comprehend context and intent. The model is developed using a substantial dataset of labelled reviews, including both positive and negative feedback, to ensure its robustness. Through thorough evaluation, the deep learning model achieves a high level of accuracy in categorizing fake reviews, providing an effective means to bolster trust and reliability in online review systems. This strategy could be integrated into current platforms, enabling real-time detection of fake reviews and protecting both users and businesses from deceptive practices.
Keywords: Fake review detection Deep learning Convolutional Neural Networks (CNNs)
Abstract
FUTURE-READY INTERFACES: RESPONSIVE & ADAPTIVE DESIGN
Ms. P. Priyadharshini, Mrs. P. Menaka
DOI: 10.17148/IJIREEICE.2025.13322
Abstract: As mobile, cloud computing, and Internet of things technologies have advanced, interface technologies have transformed into CUI, GUI, and NUI, and future developments of UI/UX are anticipated. In the present study, we demonstrated our comprehension and proficiency with the interface concerning the internet, operating system, gadgets, and contents. This study aimed to make a list of 18 items in 4 areas for basic knowledge of UI/UX, establishment of design research, designconcept, and design output for 29 IT department sophomore, junior, and senior students. The comprehension outcomes were categorised into three groups—excellent, normal, and insufficient—and assessed. Excellent was 19.35%, average was 42.53%, and insufficient was 38.12%, according to the results. As a result, 80% of students did not fully comprehend UI/UX, while 20% of students did. Specifically, the design research area received 41 points, the design content area received 43 points, and the design production area received 16 points in the comparison analysis of the four areas. It turned out to be the lowest. In the same manner as the UI/UX comprehension, the 10 assessment items in the mobile UI/UX build guide evaluation were then assessed. The average score was 80 points, the terrible score was 194 points, and the great score was 16. The evaluation of the UI/UX build guidance was lower than that of the UI/UX comprehension. Therefore, UI/UX professionals should be developed through professional course organisation and a structured curriculum in order to cultivate UI/UX comprehension and content production capacity.
Keywords: Mobile, UI/UX Trend, Design Trend, User Interface Understanding, and User Experience Understanding
Keywords: Mobile, UI/UX Trend, Design Trend, User Interface Understanding, and User Experience Understanding
Abstract
Prediction Of Cyber-Attacks Using Machine Learning Algorithms
KAMALANATHANAN S, DR. J. SAVITHA
DOI: 10.17148/IJIREEICE.2025.13323
Abstract: As cyber data attacks continue to rise, manual investigation methods are becoming increasingly inefficient, prone to errors, and time-consuming. With cyber threats evolving and attackers using similar patterns, detecting and responding to attacks in a timely manner remains a major challenge. Cyber-attacks in cyberspace aim to disrupt, disable, or take control of an organization's computing infrastructure, compromise data integrity, or steal sensitive information. The growing number of internet users and the uncertain state of cyberspace pose significant security concerns. New technological advancements and the extensive collection of big data from device sensors expose vast amounts of information, making systems more vulnerable to targeted cyber threats. Although numerous existing models and algorithms have been developed for cyber-attack prediction, there is a need for more advanced approaches that go beyond task-specific techniques.
Machine learning provides a powerful solution by framing cyber-attack prediction as a classification problem. By analyzing network datasets, supervised machine learning techniques (SMLT) can identify key patterns through variable identification, univariate and multivariate analysis, and handling missing data. A comparative analysis of various machine learning algorithms helps determine which method is most effective in predicting cyber-attacks.
Keywords: BENIGN attack, WEB attacks, SQL Injection attack, Machine learning algorithms, XSS attack, Brute Force attack, DDOS attack.
Machine learning provides a powerful solution by framing cyber-attack prediction as a classification problem. By analyzing network datasets, supervised machine learning techniques (SMLT) can identify key patterns through variable identification, univariate and multivariate analysis, and handling missing data. A comparative analysis of various machine learning algorithms helps determine which method is most effective in predicting cyber-attacks.
Keywords: BENIGN attack, WEB attacks, SQL Injection attack, Machine learning algorithms, XSS attack, Brute Force attack, DDOS attack.
Abstract
PAWPREDICT USING YOLO (You Only Look Once) FOR OBJECT DETECTION
Deepika. D.S, Santhi. K
DOI: 10.17148/IJIREEICE.2025.13324
Abstract: Ensuring home safety through effective pet monitoring is essential for pet owners, particularly in preventing potential risks associated with unattended animals. This paper presents a real-time cat detection and surveillance system designed to enhance home security and pet management. The system employs advanced object detection techniques, integrated with automated notification and alert mechanisms, to ensure timely responses. It continuously captures video feeds and images, which are pre-processed using image enhancement techniques to improve detection accuracy. An advanced object detection model analyzes these images in real-time, identifying and classifying cats based on distinctive features such as shape, texture, and movement patterns. To optimize performance, techniques such as dimensionality reduction and feature extraction are applied, reducing computational complexity while maintaining precision. Upon detecting a cat in restricted areas, the system activates automated responses, including real-time notifications to users with details such as the time of detection and location. Additionally, an auditory alert can be triggered to redirect the pet away from unsafe zones. Remote access and control functionalities allow users to manage the system from a distance, ensuring flexible and effective monitoring. The detection model is trained on a diverse dataset of labeled cat images, ensuring high classification accuracy across various lighting conditions and environments. Regular updates and retraining further improve adaptability and performance. By providing reliable, real-time cat detection and alert capabilities, this system enhances home safety, reduces potential hazards, and assists pet owners in maintaining secure and controlled indoor environments. This approach minimizes manual supervision efforts while fostering a safer coexistence between pets and household members.
Keywords: Real-time cat monitoring, home safety, object detection, pet surveillance, automated alerts, remote monitoring, machine learning
Keywords: Real-time cat monitoring, home safety, object detection, pet surveillance, automated alerts, remote monitoring, machine learning
Abstract
DEFECT TRACKING: SOFTWARE DEFECT TRACKING AND REPORTING SYSTEM
A. NEHA, DR. K. THENMOZHI
DOI: 10.17148/IJIREEICE.2025.13325
Abstract: A Software Defect Tracking and Reporting System is a critical element of the software development lifecycle (SDLC) that supports teams in managing, tracking, and resolving software application defects (or bugs) efficiently. Such systems are critical to ensuring software quality as they facilitate defect identification, documentation, and resolution from start to completion. facilitate seamless communication between development and testing teams, improving productivity and collaboration. Defect tracking systems also offer key metrics and reports that aid in prioritizing issues, root cause analysis, and driving continuous improvement in the software development process. All in all, a solid defect tracking system is central to upholding high-quality software and making timely and precise defect resolution possible.
Keywords: Defect Tracking System, Bug Management, Software Quality Assurance (QA) Software Development Lifecycle (SDLC) , Defect Reporting , Automated Defect Tracking , Bug Resolution Process , Defect Prioritization , Root Cause Analysis , Defect Metrics , Quality Control , Project Management Tools Integration , Test Case Management
Keywords: Defect Tracking System, Bug Management, Software Quality Assurance (QA) Software Development Lifecycle (SDLC) , Defect Reporting , Automated Defect Tracking , Bug Resolution Process , Defect Prioritization , Root Cause Analysis , Defect Metrics , Quality Control , Project Management Tools Integration , Test Case Management
Abstract
Machine learning-Driven Detection of Encrypted VPN Traffic in enterprise networks
Vignesh.M, Dr Shanthini. S
DOI: 10.17148/IJIREEICE.2025.13326
Abstract: Recent abuse of Virtual Private Networks (VPNs) has introduced significant challenges in network monitoring for enterprises, particularly with the rise of encrypted traffic that obscures legitimate from malicious activities. Malicious traffic is increasingly routed through VPNs, making it difficult to detect unauthorized data transfers. Traditional traffic analysis tools are ineffective at identifying encrypted VPN traffic, leaving networks vulnerable to attacks. This paper presents a machine learning-based framework designed to detect encrypted VPN traffic within enterprise networks. By analyzing network flow data, the framework extracts relevant features to train machine learning models that identify anomalous traffic patterns, which often indicate malicious activity. The system incorporates both supervised and unsupervised learning algorithms for the detection and classification of VPN traffic, providing an advanced method for monitoring encrypted communications. Experimental results demonstrate that machine learning models can significantly improve the detection of VPN traffic, offering a scalable, non-intrusive solution for securing networks. The framework allows organizations to maintain high security levels without compromising user privacy or decrypting encrypted communications. This system adds to the growing collection of effective solutions aimed at addressing the challenge of securing networks while managing VPN traffic.
Keywords: Machine Learning, VPN Traffic, Detection, Network Security, Encrypted Communications, Anomaly Detection
Keywords: Machine Learning, VPN Traffic, Detection, Network Security, Encrypted Communications, Anomaly Detection
Abstract
Indian traffic sign detection and recognition using deep learning
Mr. M. Lokesh, Mrs. P. Menaka, M.C.A., M.Phil., (Ph.D.),
DOI: 10.17148/IJIREEICE.2025.13327
Abstract: Traffic signs are essential in regulating traffic on the road, guiding drivers, thus helping to avoid injuries, property damage, and deaths. Managing traffic signs with automatic detection and recognition is a significant component of any Intelligent Transportation System (ITS). In the age of self-driving vehicles, the importance of automatic detection and recognition of traffic signs cannot be emphasized enough. This paper introduces a deep-learning-driven autonomous approach for the identification of traffic signs in India. The automatic detection and recognition of traffic signs were designed using a Convolutional Neural Network (CNN)- Refined Mask R-CNN (RM R-CNN)-based end-to-end learning framework. The proposed concept was evaluated using an innovative dataset featuring 6480 images that included 7056 instances of Indian traffic signs categorized into 87 classes. We provide multiple enhancements to the Mask R-CNN model in terms of both architecture and data augmentation. We introduce multiple improvements to the Mask R-CNN model, both in terms of architecture and data augmentation. We have examined particularly difficult Indian traffic sign categories that have not been documented in earlier research. The dataset for training and testing our proposed model is gathered by taking images in real-time on Indian roads. The evaluation findings show an error rate of less than 3%. Additionally, the performance of RM R-CNN was contrasted with traditional deep neural network architectures like Fast R-CNN and Mask R-CNN. Our proposed model attained a precision of 97. 08%, which surpasses the precision achieved by the Mask R-CNN and Faster R-CNN models.
Keywords: Traffic Signs, Intelligent Transportation System (ITS), Refined Mask R-CNN (RM R-CNN), Indian Traffic Signs Dataset, Deep Learning, Real-time Image Processing, Data Augmentation, Precision Rate.
Keywords: Traffic Signs, Intelligent Transportation System (ITS), Refined Mask R-CNN (RM R-CNN), Indian Traffic Signs Dataset, Deep Learning, Real-time Image Processing, Data Augmentation, Precision Rate.
Abstract
MACHINE LEARNING APPROACHES FOR CO2 EMISSION ANALYSIS IN TRANSPORTATION
R. LEELA VARSHINI, DR. K. THENMOZHI
DOI: 10.17148/IJIREEICE.2025.13328
Abstract: Growing attention to weather trade and environmental sustainability has emphasised the need to control and reduce carbon dioxide (CO2) emissions. As the transportation sector contributes extensively to greenhouse gas emissions, there is a need for the specific evaluation of car overall performance in phrases of CO2 emissions. This study explores the utility of facts and science techniques to research and increase versions and expects CO2 emissions from motors and gas lessons. Using statistics from respectable and business assets, including gas efficiency, engine specifications and emissions checking out effects, the examine makes use of gadget gaining knowledge of algorithms and mathematical fashions to categorise cars in percentage to their CO2 emissions Basic methods for dealing with missing objectives and by way of-merchandise Information consists of preprocessing, exploratory statistics analysis to perceive emission patterns, and forecasting modelling of destiny emission trends primarily based on automobile configuration and gasoline financial system. In addition to the use of superior strategies which include feature engineering, clustering, and regression analysis to become aware of elements affecting emissions, such as engine length, vehicle weight, and drivetrain characteristics, the look at includes geography and time of additives are blanketed to apprehend emission changes throughout areas and over the years. The findings aim to provide actionable perspectives for policymakers, builders, and users.
Keywords: CO2 emissions, vehicle emission rating, data science in transportation, carbon footprint, greenhouse gas emissions, emission prediction models, machine learning for emissions, fuel efficiency, sustainable transportation, and emissions standards
Keywords: CO2 emissions, vehicle emission rating, data science in transportation, carbon footprint, greenhouse gas emissions, emission prediction models, machine learning for emissions, fuel efficiency, sustainable transportation, and emissions standards
Abstract
RESCUE WINGS WEB COMPUTING AND ACTIVE SERVICES SUPPORT SYSTEM FOR DISASTER RESCUE
SAI SHANKARI V, Dr. J. SAVITHA M.Sc., M.Phil., Ph.D
DOI: 10.17148/IJIREEICE.2025.13329
Abstract: The initiative "Rescue Wings: A Web-Based Computing and Active Services Support System for Disaster Response" involves sending a request to the relevant organization for assistance in rescuing individuals trapped in a disaster. The primary goal of this project is to aid those in distress. Upon receiving a request from the public, the organization assigns workers to assist those affected by the crisis. As workers carry out rescues, updates will be communicated to the public via email. Individuals who develop innovative rescue equipment can register their information and upload a video along with a description of their invention. The administrator reviews the video, and if it meets the criteria, it will be approved; otherwise, it will be rejected. The administrator is responsible for maintaining comprehensive records of the company, workers, and members of the public who request assistance, as well as details pertaining to the submitted videos. As rescue operations progress, updates are shared with the public via email to ensure transparency and keep affected individuals updated. Beyond immediate rescue efforts, the platform fosters innovation by enabling the public to propose videos and descriptions of potential rescue equipment inventions. These proposals are assessed by an administrator, who approves feasible solutions for implementation in disaster response. Additionally, the system keeps thorough records of responders, the organization, and public requests, facilitating an organized approach to disaster management. This initiative aims to enhance the effectiveness of rescue operations, encourage public participation, and harness inventive solutions during crises, ultimately leading to saved lives and improved disaster response capabilities.
Keywords: Disaster Response ,Rescue operations, web-based requests
Keywords: Disaster Response ,Rescue operations, web-based requests
Abstract
The Dark Web: An Examination of the Internet’s Shadowy Areas
Mr. G. Balaji, Mrs. P. Menaka, M.C.A., M.Phil., (Ph.D.,)
DOI: 10.17148/IJIREEICE.2025.13330
Abstract: There are two primary parts of the Internet: the "Deep Web" and the "Surface Web." The Deep Web consists of unindexed pages, while the Surface Web consists of all publicly accessible and indexed websites. Because it contains hidden content on the World Wide Web, the "dark web" makes up the largest portion of the Deep Web. Certain software, authentication, and settings are required in order to use it. A multi-layer encryption method called the Onion Router, or TOR, safeguards user confidentiality and privacy. Numerous studies and surveys indicate that most internet users think the deep web and the dark web are interchangeable. To shed light on this and analyze the structure of the Internet, this article explores the current composition of the Internet and that section of the World Wide Web, which includes the Surface Web, Deep Web, and Dark Web. This phrase highlights the benefits of utilizing the Tor browser in the dark web and its useful applications while outlining the differences between the deep web and the dark web.
Keywords: Dark web, deep web, encryption, TOR, anonymous, privacy, access.
Keywords: Dark web, deep web, encryption, TOR, anonymous, privacy, access.
Abstract
DETECTION OF CYBERBULLYING ON SOCIAL MEDIA USING MACHINE LEARNING
S. DHANUSRI, DR. J. SAVITHA
DOI: 10.17148/IJIREEICE.2025.13331
Abstract: Cyberbullying has emerged as a serious issue in recent years with the growth of social media, which has created serious psychological and emotional effects on victims. This study aims to identify cyberbullying through machine learning methods for automatic classification and identification of abusive content. The work analyzes various natural language processing (NLP) techniques for feature extraction, including TF- IDF, word embeddings, and sentiment analysis, to enhance detection accuracy. Support Vector Machines (SVM), Random Forest, and deep learning models like LSTMs and transformers are used for classification. Real-world social media data are used in the dataset to enable robust training and cross-validation of models. Performance measures such as precision, recall, and F1-score are used to compare various methodologies. The results indicate that the newest deep learning models, particularly transformer-based ones, are far better at detecting cyberbullying than traditional methods with a great accuracy rate. The research contributes to constructing independent tools for the early identification of cyberbullying, promoting a safer online community.
Keywords: Cyberbullying detection, social media monitoring, Machine learning classification, Natural Language Processing (NLP), Text classification, Toxicity detection.
Keywords: Cyberbullying detection, social media monitoring, Machine learning classification, Natural Language Processing (NLP), Text classification, Toxicity detection.
Abstract
FISHERMEN BORDER ALERT SYSTEM USING IOT
LOGA SABARI M, Dr. R.PRABA
DOI: 10.17148/IJIREEICE.2025.13332
Abstract: The current marine security challenge includes protecting fishermen and responding to illegal border infiltration. Using the Internet of Things (IoT), this study created a technique for enhancing border detection that largely leverages the Automatic Detection System (AIS) to determine the boundary for fishermen. Very High Frequency (VHF) communication, inspired by X-band radar, is integrated into the proposed idea to provide highly accurate boat detection in the middle of the sea. The system can recognize and track vessels at sea. The system architecture included VHF (Very High Frequency) communication, which was modeled after the X band radar system, to provide the middle sea with a high level of boat detection and monitoring. The breadth of AIS.
The suggested approach uses Very High Frequency (VHF) communication, which was influenced by X-band radar, to give highly accurate boat detection in the middle of the sea. Boats at sea can be detected and tracked by the system. Inspired by the X band radar system, the system architecture integrated VHF (Very High Frequency) transmission to give the middle sea a high level of boat detection and surveillance. VHF transmission was used to extend the AIS's range. Using IoT devices, fishing boats provide position and status data to the coastal monitoring stations. Fishing boats equipped with IoT-enabled devices are part of the new AIS technology. After sending data, the IoT devices installed aboard boats transmit information to the coastal monitoring station. In addition to the introduction of the Internet of Things (IoT), the Automatic Identification System (AIS) currently in use has been improved. As a result, the system can now communicate with marine vessels and track and monitor them in a far more thorough and real-time manner.
Keywords: GPS, maritime border, proximity warning, geo-fencing, GSM, microcontroller, latitude/longitude, boundary line, safety zone, danger zone, distress signal, weather alerts, IoT (Internet of Things), proximity warning, fishing vessel, and coastal security.
The suggested approach uses Very High Frequency (VHF) communication, which was influenced by X-band radar, to give highly accurate boat detection in the middle of the sea. Boats at sea can be detected and tracked by the system. Inspired by the X band radar system, the system architecture integrated VHF (Very High Frequency) transmission to give the middle sea a high level of boat detection and surveillance. VHF transmission was used to extend the AIS's range. Using IoT devices, fishing boats provide position and status data to the coastal monitoring stations. Fishing boats equipped with IoT-enabled devices are part of the new AIS technology. After sending data, the IoT devices installed aboard boats transmit information to the coastal monitoring station. In addition to the introduction of the Internet of Things (IoT), the Automatic Identification System (AIS) currently in use has been improved. As a result, the system can now communicate with marine vessels and track and monitor them in a far more thorough and real-time manner.
Keywords: GPS, maritime border, proximity warning, geo-fencing, GSM, microcontroller, latitude/longitude, boundary line, safety zone, danger zone, distress signal, weather alerts, IoT (Internet of Things), proximity warning, fishing vessel, and coastal security.
Abstract
LEVERAGING MACHINE LEARNING ALGORITHM FOR DETECTING PSYCHOLOGICAL INSTABILITY
S. KEERTHANA, DR. K. SANTHI
DOI: 10.17148/IJIREEICE.2025.13333
Abstract: In the contemporary era, people are moving towards the achievement of ‘goals’ as dictated by society and in the process, they often overlook their emotional and psychological health. There are quite a few health issues that society has been trying to address, the most concerning being psychological issues – depression, stress, etc. Failing to treat these issues can then lead to a range of mental health illnesses, for example, someone with bipolar disorder, which can lend up to be heart-wrenching. In order to mitigate the extent of these occurrences, it is critical to find and treat the affected areas promptly. This research aims to develop a model using machine learning that will be able to detect indications of despondency – the feeling of hopelessness. Working professionals were the subjects and given an array of questions through which depressive characteristics could be detected. A variety of machine learning methodologies were used to assess and categorize the information. A Random Forest algorithm delivered the best result among them, with an 87.02% accuracy rate and better precision and dependability than other approaches. Many conclusions were reached as a result of the study, the most striking being how machine learning can be used to detect any patterns to mental health illnesses, thus detection could potentially be quicker. In harnessing such data-oriented strategies, this paper provides an instrument that is easy to implement and can be used at scale for assessing mental well-being.
Keywords: depression detection, bipolar disorder, stress analysis, Random Forest algorithm, despondency detection, working professionals, predictive modelling , dataset analysis, mental health assessment.
Keywords: depression detection, bipolar disorder, stress analysis, Random Forest algorithm, despondency detection, working professionals, predictive modelling , dataset analysis, mental health assessment.
Abstract
Secure Application Using Multifactor Authentication
K. Naveen, Dr. K. Santhi
DOI: 10.17148/IJIREEICE.2025.13334
Abstract: The advancing techniques of sophisticated cyber attacks have rendered the traditional methods of password- based authentication incapable of securing sensitive information or user accounts. The authentication that this project deals with integrates One-Time Passwords (OTPs) and CAPTCHAs in a multi-layered security approach. OTPs, delivered via SMS, email, or authenticator apps, ensure that only authorized users may access an account by entering a code with a limited lifetime. CAPTCHAs, unlike an OTP, take the approach of distinguishing between human users and bots through various challenges such as image recognition or text puzzles, which prove useless against automated attacks. These two mechanisms circumvent the problems delineated by traditional passwords and greatly improve the protection of information against phishing, brute thing attacks, and unauthorized access. Usability is front and center in the system design, and as such, it provides features like real-time feedback, accessibility characteristics, and ways to sometimes reduce friction for trusted users. It is applicable in diverse fields such as banking, e-commerce, and social media, where securing user data and preventing fraud is paramount. Although there exist challenges, such as user resistance, technical issues, and evolving threats, the system provides an opportunity for a scalable and tactical solution that upholds a user's experience closely in balance to security. The project proposes an online security enhancement through trust generation among users on a digital platform by leveraging strengths offered by OTP and CAPTCHA towards building a secure authentication framework.
Keywords: One-Time Password (OTP), CAPTCHA, authentication, cybersecurity
Keywords: One-Time Password (OTP), CAPTCHA, authentication, cybersecurity
Abstract
A MODULAR EVENT MANAGEMENT SYSTEM WITH REAL-TIME COLLABORATION AND ONLINE BOOKING FEATURES
Rithanya.P.M, Santhi. K
DOI: 10.17148/IJIREEICE.2025.13335
Abstract: The Event Management System (EMS) is sophisticated, web-based platform created to streamline event planning, improve efficiency, and minimize time-intensive processes. This system offers a variety of tools to help organizers plan, coordinate, and execute events with ease. The platform simplifies key aspects of event management such as invitation handling, venue selection, catering and entertainment management, transportation logistics, and even managing event-specific media. By streamlining these tasks, EMS significantly reduces the amount of manual work involved, while also improving collaboration between event organizers, vendors, and other stakeholders. The system demonstrates the application of modern web technologies in creating a practical, user-friendly solution to the challenges faced in event coordination.
Keywords: Event Management System, Web Application, Database Design, System Architecture, Resource Management, Automation.
Keywords: Event Management System, Web Application, Database Design, System Architecture, Resource Management, Automation.
Abstract
Sustainable Agriculture Marketplace
Ms. C. Divyabharathi, Dr. K. Banuroopa, M.CA., M.Phil., Ph.D.
DOI: 10.17148/IJIREEICE.2025.13336
Abstract: The agricultural sector is a cornerstone of global food production. With the growing demand for organic products and the challenges presented by middlemen in traditional supply chains, the need for a more efficient, cost- effective, and sustainable approach has never been greater. This project aims to bridge the gap between farmers and consumers by creating a marketplace that directly connects them, allowing for the direct exchange of organic produce. By reducing intermediaries, the initiative ensures that farmers receive fair prices for their products, while consumers gain access to fresh, organic food at a reasonable cost. The platform fosters transparency, optimizes agricultural productivity, and promotes sustainable practices, ultimately benefiting both farmers and consumers.
Keyword: Organic farming, Direct farm-to-consumer, Fair pricing for farmers, Organic produce, Supply chain optimization, Digital farming platform.
Keyword: Organic farming, Direct farm-to-consumer, Fair pricing for farmers, Organic produce, Supply chain optimization, Digital farming platform.
Abstract
AI-Powered Cloud Computing: Transforming the Digital Landscape
Ms. G. Santhiya, Mrs. P. Menaka, M.C.A., M.Phil., (Ph.D.)
DOI: 10.17148/IJIREEICE.2025.13337
Abstract: The integration of Artificial Intelligence (AI) and Cloud Computing is revolutionizing industries by enhancing the management and utilization of cloud resources. AI’s capability to process vast amounts of data and generate insights is transforming cloud environments, enabling dynamic scalability, efficient resource allocation, and improved operational performance. By leveraging AI-driven tools and algorithms, cloud computing benefits from automation in routine tasks like system monitoring and maintenance, reducing costs and minimizing human errors. Additionally, sophisticated AI models enhance data analytics, allowing businesses to derive meaningful insights from large datasets and make real-time, data-driven decisions. Machine learning and predictive analytics further refine cloud-based applications by improving forecasting accuracy and delivering personalized user experiences. AI also strengthens cloud security by identifying and mitigating potential threats more effectively. Moreover, the fusion of AI and cloud computing fosters innovation in areas such as intelligent data storage and management. Together, these technologies are shaping the future of digital infrastructure, offering scalable, efficient, and intelligent solutions that drive progress and innovation.
Keywords: AI, Cloud Technology, Data Insights, Machine Learning, and Efficient Resource Management.
Keywords: AI, Cloud Technology, Data Insights, Machine Learning, and Efficient Resource Management.
Abstract
ANTI PIRACY SOFTWARE PROTECTION TOOL
BHUVANESH. J, Dr. R. PRABA
DOI: 10.17148/IJIREEICE.2025.13338
Abstract: This project is designed to protect software from piracy and ensure that it can only be accessed by authorized users. With software piracy being such a huge issue on the internet, it poses a significant threat to software companies. Hackers can use malicious programs to break into systems, steal software, and use it illegally. That’s why there’s a need for a system that protects both the software and the users from theft and misuse. The purpose of this project is to create a Software License Management System that works over the internet or intranet. It helps prevent hackers from using pirated software by generating and verifying serial keys remotely. The system keeps track of important details like the number of licenses sold, the type of license, the license number, serial keys, number of users, and the validity of each license. This system makes sure that only legitimate, paid users can install and use the software. It verifies the license at the time of installation and stops the installation process if the software is pirated. All information about sold software and license transactions is securely stored in a centralized database for easy verification. Additionally, the system allows users to register their software and product details online. These details are securely stored in the database, and the serial keys are encrypted to prevent hackers from stealing them. Users also get email alerts and reminders to keep them informed about software updates and license renewals
Abstract
Promoting Women’s Safety: A GPS-Enabled Internet of Things Tracking System
Ms. S. Monisha, Dr. J. Savitha, M.Sc., M.Phil., Ph. D
DOI: 10.17148/IJIREEICE.2025.13339
Abstract: The safety and well-being of women is a vital concern in today's society. This research proposes an innovative solution that merges Internet of Things (IoT) technology with GPS tracking to tackle this problem. The solution consists of a compact, easy-to-use IoT button with GPS, designed to enhance women’s security in various circumstances. Small and portable, this GPS-enabled button can be discreetly carried. Once activated, it uses GPS to determine the user's location and syncs with a mobile app to deliver real-time location information and send instant alerts to chosen contacts or authorities. This technology based solution provides women with a proactive and responsive safety tool, improving their personal security. By incorporating cutting-edge technology, this solution ensures its reliability and effectiveness in addressing safety concerns, supporting the ongoing efforts to create safer spaces for women.
Keyword: Women's security, IoT technology, GPS monitoring, Location tracking system, Individual safety.
Keyword: Women's security, IoT technology, GPS monitoring, Location tracking system, Individual safety.
Abstract
A Machine Learning-based System for Fake Profile Identification
S. DHARSHAN, S. SAKTHI VEL, S.S. KISHORE, DR.K. THENMOZHI
DOI: 10.17148/IJIREEICE.2025.13340
Abstract: Online social networks have permeated our social lives in the current generation. These sites have allowed us to see our social lives differently than they did in the past. Nowadays we can connect with new friends and maintain relationships with them via social and personal activities become quite easy. Online Social Networks (OSN) are contributed in all areas such as Research in all domains, Job-related areas, Technology oriented areas, Health care, and business-oriented areas, Information gathering and data collection, and so on. One of the biggest problems on these social media platforms is fake profiles. Impersonating to be someone else and causing harm and defamation to the real person or advertising or popularizing removed propaganda on someone’s name to get more benefit is the motto of such profile creators. There have been many studies regarding these fake accounts and how can they be mitigated. Many approaches such as graph-level activities or feature analysis have been taken into consideration to identify fake profiles. These methods are outdated when compared to arising issues of these days. In this paper, we proposed a technique using machine learning for fake profile detection which is efficient.
Keyword: Fake profile, Detection, Machine Learning, social media, Instagram, Internet.
Keyword: Fake profile, Detection, Machine Learning, social media, Instagram, Internet.
Abstract
Agri-Trade Platform
Mr. A. Aakash, Dr. S. Shanthini, M.Sc., M.Phil., Ph.D.
DOI: 10.17148/IJIREEICE.2025.13341
Abstract: Agriculture is the backbone of many economies around the world, feeding billions of people daily. However, the agricultural industry faces significant challenges, including access to modern farming machinery, the availability of quality animal feeds, and the timely supply of other critical field products. The Agri-Trade Platform is proposed to address these challenges by offering an integrated online marketplace where farmers can easily access and purchase agricultural machinery, animal feeds, fertilizers, seeds, and other products. This journal explores the importance of the Agri-Trade Platform in revolutionizing the agricultural supply chain, improving efficiency, reducing costs, and fostering sustainability in farming practices.
Keywords: Online farming marketplace, Agricultural machinery, Fertilizer availability , Grains and cereals sourcing , Farming tools and equipment , Agricultural blogs.
Keywords: Online farming marketplace, Agricultural machinery, Fertilizer availability , Grains and cereals sourcing , Farming tools and equipment , Agricultural blogs.
Abstract
WATER PIPELINE LEAKAGE DETECTION USING IOT
SUMETHA R G, Dr. R. PRABA
DOI: 10.17148/IJIREEICE.2025.13342
Abstract: Water pipeline leakage is a critical challenge that leads to the wastage of valuable water resources, increased operational costs, infrastructure damage, and environmental hazards. Traditional methods of leak detection, such as manual inspections and acoustic sensing, often suffer from high labor costs, time inefficiency, and limited detection accuracy. Therefore, there is a growing demand for automated, intelligent, and real-time leak detection systems that can accurately identify leaks and prevent potential water losses. In this project, we propose an AI-powered pipeline leakage detection system by developing a custom one-dimensional Time-Series Dense Net model integrated with multi-sensor data fusion. The system employs an array of Light Dependent Resistor (LDR) sensors to monitor changes in light intensity within the pipeline, temperature sensors to detect unusual heat variations, and wet sensors to identify the presence of leaked water. These sensors are strategically placed along the pipeline network to ensure comprehensive monitoring of potential leakage points. An ESP32 microcontroller is utilized to collect real-time sensor data, preprocess the readings, and transmit them to a central processing unit for analysis. the collected time-series data is fed into a customized Time-Series Dense Net model, which is optimized to process sequential data efficiently. Dense Net’s architecture, known for feature reuse and gradient flow efficiency, is adapted to handle one-dimensional sensor input, enabling it to detect subtle, complex patterns associated with water leaks. By leveraging the strengths of Dense Net, the proposed model ensures high accuracy in distinguishing normal pi line conditions from potential leaks based on real-time sensor fluctuations. Additionally, the system is designed to provide early warning notifications through an IoT- enabled dashboard that visualizes sensor readings, predicts leakage probability, and alerts maintenance personnel via SMS, email, or mobile app notifications. This proactive approach minimizes water losses, reduces operational costs, and enhances pipeline maintenance efficiency.
Abstract
RAINFALL PREDICTION SYSTEM USING MACHINE LEARNING ALGORITHM
Winmaniraja. B, Santhi. K
DOI: 10.17148/IJIREEICE.2025.13343
Abstract: Accurate rainfall prediction is critical for water resource management, agriculture, and disaster mitigation. Traditional meteorological models often struggle to account for complex patterns in rainfall data. This paper presents a machine learning-based rainfall prediction system using meteorological data features such as temperature, humidity, pressure, and wind speed. Three models—Linear Regression, Random Forest, and XGBoost—are implemented and compared in terms of accuracy and predictive performance. The study finds that ensemble models such as Random Forest and XGBoost significantly outperform traditional linear models, reducing prediction errors and improving forecast accuracy.
Keywords: Rainfall Prediction, Machine Learning, Weather Forecasting, Meteorological Data, Random Forest, XGBoost, Linear Regression, Time Series Analysis, Feature Importance, Data Preprocessing, Hydrological Forecasting, Climate Modeling, Artificial Intelligence, Ensemble Learning, Prediction Models.
Keywords: Rainfall Prediction, Machine Learning, Weather Forecasting, Meteorological Data, Random Forest, XGBoost, Linear Regression, Time Series Analysis, Feature Importance, Data Preprocessing, Hydrological Forecasting, Climate Modeling, Artificial Intelligence, Ensemble Learning, Prediction Models.
Abstract
THE ROLE OF AI AND MACHINE LEARNING IN THE EVOLUTION OF PLANT SCIENCE
Dr. K. Thenmozhi, Nandika. M, Abishri. S
DOI: 10.17148/IJIREEICE.2025.13344
Abstract: Within the next few years, breakthroughs in Artificial Intelligence (AI) are going to cause a revolution in the field of botany. AI is already changing how we study green plants, their ecosystem, and how we grow crops. With the use of machine learning, computer vision, and data analysis, scientists are learning to identify species of plants with incredible accuracy, oversee ecosystems down to the finest details, and even maximize yields as never before. Such advancements can transform agriculture as farmers will spend resources efficiently, anticipate harvests accurately, and control diseases and pests more successfully. Without a doubt, such improvements will change the paradigm of agriculture as it is known today and that is why advancements in AI are so thrilling. Nonetheless, a multidisciplinary effort is vital in yielding the full benefits of AI in botany.By uniting instead of dividing, the true essence of this technology is unleashed, creating a better world in the long run.
Keywords: Introduction - intersection of Botany and Technology - Applications of AI – Key Aspects - Adoption - Cellular Measurement - Advantage of AI Adoption - Advantage – Disadvantage of AI.
Keywords: Introduction - intersection of Botany and Technology - Applications of AI – Key Aspects - Adoption - Cellular Measurement - Advantage of AI Adoption - Advantage – Disadvantage of AI.
Abstract
Enhanced Secure Cloud Storage Using Cryptographic Role-Based Access
DHARUN. R, Dr. SHANTHINI. S
DOI: 10.17148/IJIREEICE.2025.13345
Abstract: In a cloud data storage system, the data owners would wish to specify the policies as to who can access their data and the cloud providers are required to correctly enforce the policies that the data owners have specified. In order to enforce the specified access control policies before putting the data on to the cloud, the data owners can encrypt the data in the way that only users that the owners wished to allow as specified in the access control policies are able to decrypt and access the data.In this paper, we propose trust models to reason about and to improve the security for stored data in cloud storage systems that use cryptographic RBAC schemes. The trust models provide an approach for the owners and roles to determine the trustworthiness of individual roles and users, respectively, in the RBAC system. The proposed trust models consider role inheritance and hierarchy in the evaluation of trustworthiness of roles. We present a design of a trust-based cloud storage system, which shows how the trust models can be integrated into a system that uses cryptographic RBAC schemes. We have also considered practical application scenarios and illustrated how the trust evaluations can be used to reduce the risks and to enhance the quality of decision making by data owners and roles of cloud storage service[1].
Keywords: Cryptographic RBAC, Cloud Data Security, Trust- Based Access Control, Secure Data Management, Role-Based Authorization
Keywords: Cryptographic RBAC, Cloud Data Security, Trust- Based Access Control, Secure Data Management, Role-Based Authorization
Abstract
AES Based Image Encryption and Decryption for Secure Data Transfer
R. Sriman, Dr. K. Santhi
DOI: 10.17148/IJIREEICE.2025.13346
Abstract: With the rise of digital communication, ensuring secure image transmission is crucial to prevent unauthorized access and cyber threats. The Advanced Encryption Standard (AES) is a powerful symmetric encryption algorithm that efficiently encrypts and decrypts image data, ensuring confidentiality and integrity. This paper explores the implementation of AES for secure image transfer, transforming pixel values into encrypted form to prevent interception. The decryption process accurately restores the original image using the same key. Performance metrics such as encryption speed, key sensitivity, and resistance to attacks are analyzed. While AES is highly secure, challenges like computational overhead necessitate optimization and hybrid encryption approaches. Future research aims to enhance AES with AI, blockchain, and quantum cryptography for improved security and efficiency.
Abstract
Automated LED Notification System for Ambulance Alert in High Density Traffic
Kiruthika. N, Shanthini. S
DOI: 10.17148/IJIREEICE.2025.13347
Abstract: Urban traffic management remains an important concern as high-density traffic causes congestion, delays, and emergency- related challenges. This paper involves an automated LED notification system that uses computer vision and deep learning for vehicle detection and classification, with a focus on alerting and prioritizing emergency vehicles like ambulances in high- traffic density areas. Continuous transmission of traffic data from the webcam is processed with the YOLO model, which is chosen for its speed and accuracy in dynamic environments such as roads and streets, enabling quality detection and counts in various lanes. The system classifies vehicles in real time and distinguishes emergency vehicles such as ambulances from general traffic, thus enabling automated LED alerts to notify other vehicles to make way for emergency vehicles. Embedded Deep Reinforcement Learning is the core of this programming system; it connects variable lanes to dynamic timing of lights via intelligent lane allocation, aiming to reduce congestion and maximize response time for emergency vehicles. The DRL agent is self-trained using historical records and real-time feedback to improve traffic flow and prioritization for ambulances, with advances in LED notifications and traffic light synchronization using computer vision. Managing congestion is aided by providing real-time information, such as lane counts, average speed, and traffic flow, which can be useful to operators. Once any lane is recognized as having an ambulance, it is immediately tagged as a "high priority" lane, triggering the LED notification system to alert other vehicles and coordinate traffic signals for immediate clearance. Through these measures, the system improves traffic efficiency and emergency response in high-density areas.
Keywords: IoT, Radio Frequency, Microcontrollers, Arduino UNO, Transmitters, Receivers
Keywords: IoT, Radio Frequency, Microcontrollers, Arduino UNO, Transmitters, Receivers
Abstract
AN OVERVIEW OF MACHINE LEARNING: KEY CONCEPTS, METHODS, APPLICATIONS, AND THE ROLE OF PROGRAMMING LANGUAGES IN ADVANCING AI
Ms. A. Brundha, Dr.K. Thenmozhi., M.Sc., M.Phil., Ph.D.,
DOI: 10.17148/IJIREEICE.2025.13348
Abstract: Machine Learning is the field that combines both art and science, allowing machines to acquire knowledge without needing explicit programming. It integrates mathematics and computer science in a balanced way. Many people are often discouraged by the complex mathematical equations and theories that are part of machine learning. The last year has been particularly fruitful for AI and Machine Learning, with numerous groundbreaking applications emerging, especially in areas like healthcare, finance, speech recognition, augmented reality, and advanced 3D and video technologies. In the field of machine learning, programming languages ranging from Python to SQL are commonly utilized. This paper explores the concept of machine learning, its various types, and how it functions. It also delves into the key components of machine learning and provides an overview of the methods currently in use, along with their processes, applications, benefits, and limitations. Additionally, we highlight the top seven programming languages used in machine learning and discuss the companies that are leveraging machine learning technologies.
Keywords: ML algorithms, machine learning (ML), and traditional programming.
Keywords: ML algorithms, machine learning (ML), and traditional programming.
Abstract
ENHANCING SOLAR PANEL EFFICIENCY WITH IOT AND CLOUD TECHNOLOGIES
Thirumalai Kumar G, Lawrance J, Murshath Basha I, Seetharaman R*
DOI: 10.17148/IJIREEICE.2025.13349
Abstract: The increasing demand for renewable energy necessitates efficient monitoring of solar panel performance. This paper presents an IoT-based solar panel monitoring system using ESP-32 and Blynk to enable real-time data collection and remote monitoring. The system integrates voltage, current, temperature, and humidity sensors to assess the panel’s efficiency. The ESP-32 microcontroller processes sensor data and transmits it to the Blynk cloud, allowing users to monitor power generation through a mobile application. A liquid crystal display (LCD) provides live readings, while WiFi connectivity ensures seamless data transmission. This system enhances energy management by enabling predictive maintenance, early fault detection, and improved efficiency analysis. The proposed solution offers a cost- effective, scalable, and user-friendly approach to solar energy monitoring, contributing to the advancement of smart renewable energy systems. Future work may include automated load balancing, machine learning-based performance optimization, and integration with grid systems to maximize solar energy utilization
Keywords: IoT-based monitoring, ESP-32, Blynk cloud, solar panel efficiency, renewable energy, real-time data transmission, smart energy management, wireless sensor network.
Keywords: IoT-based monitoring, ESP-32, Blynk cloud, solar panel efficiency, renewable energy, real-time data transmission, smart energy management, wireless sensor network.
Abstract
THE IMPACT OF UBRANIZATION ON AGRICULTURE AND FOOD SECURITY
SIVARANJANI S, Dr. K. THENMOZHI
DOI: 10.17148/IJIREEICE.2025.13350
Abstract: Urbanization significantly impacts agriculture and food security by reducing the availability of arable land and increasing competition for natural resources. As cities expand, agricultural lands are converted into residential, industrial, and commercial areas, leading to a decline in food production capacity. Urbanisation also drives changes in dietary patterns and increases the demand for processed and imported foods, putting pressure on local food systems. Furthermore, rural-to-urban migration results in labour shortages in agriculture, affecting productivity. However, urbanisation also presents opportunities for innovative solutions, such as urban farming, vertical agriculture, and improved supply chain infrastructure, which can enhance food security. Strengthening rural-urban linkages and promoting sustainable agricultural practices are essential to mitigating the negative effects of urbanisation on food security and ensuring resilient food systems.
Keywords: Urbanisation, agriculture, food security, land conversion, ruralto-urban migration, urban farming, supply chain, sustainable agriculture.
Keywords: Urbanisation, agriculture, food security, land conversion, ruralto-urban migration, urban farming, supply chain, sustainable agriculture.
Abstract
A COMPREHENSIVE WEB DATA EXTRACTION SYSTEM: ARCHITECTURE, IMPLEMENTATION, AND ANALYSIS
RAGUNANTHAN.S, Dr. R. PRABA
DOI: 10.17148/IJIREEICE.2025.13351
Abstract: In the era of digital transformation, this paper introduces an innovative web data extraction system that revolutionizes online information collection and analysis using Python's Flask framework. Our solution addresses existing limitations through a unified architecture comprising three interconnected modules: an intelligent scraping engine, analytics framework, and secure data management system. The hybrid approach integrates traditional HTML parsing with dynamic content rendering capabilities, enabling accurate extraction from modern JavaScript and AJAX- based applications. Experimental results from a three-month deployment demonstrate a 60% reduction in extraction time and 45% improved accuracy for dynamic content processing, with applications spanning market research, competitive analysis, academic data collection, and trend monitoring. This research advances web data extraction methodology while establishing a foundation for future developments in automated data collection, demonstrating the transformative potential of intelligent web scraping systems for organizational data gathering within ethical and technical boundaries.
Keywords: Web Scraping, Data Extraction, Real-time Analytics, E-commerce Analysis, Dynamic Content Processing, Information Retrieval, Python Flask, Web Automation
Keywords: Web Scraping, Data Extraction, Real-time Analytics, E-commerce Analysis, Dynamic Content Processing, Information Retrieval, Python Flask, Web Automation
Abstract
REAL-TIME VEHICLE SPEED DETECTION USING PYTHON
MANIKANDAN. V, Dr. R. PRABA
DOI: 10.17148/IJIREEICE.2025.13352
Abstract: This paper presents a practical approach to detecting and estimating vehicle speeds in real time using video image processing techniques. The system utilizes object detection algorithms to identify vehicles in video frames and calculates their speeds by analyzing motion between consecutive frames. Designed to be both cost-effective and adaptable, this method provides a scalable solution for traffic monitoring and law enforcement applications. The backbone of the system lies in feature extraction and motion analysis, which are optimized to handle varying environmental conditions such as low lighting, adverse weather, and high traffic density. Frames extracted at regular intervals are preprocesses to enhance quality and reduce computational load, while convolutional neural networks (CNNs) enable the accurate detection of vehicles through learned spatial and temporal patterns. Speed estimation is achieved by calculating the displacement of detected vehicles across frames, with calibrations accounting for camera angles and dimensions. A key innovation of the proposed system is its modular architecture, allowing seamless integration with smart city ecosystems and IoT-enabled traffic infrastructures. The real-time processing capability of the system enables instant feedback for traffic regulation and speed enforcement, which can significantly reduce accidents and ensure road safety.
Keywords: Real-time vehicle speed detection, video image processing, object detection algorithms, convolutional neural networks (CNNs), motion analysis, traffic monitoring, speed estimation, modular architecture, IoT-enabled infrastructure, road safety enhancement.
Keywords: Real-time vehicle speed detection, video image processing, object detection algorithms, convolutional neural networks (CNNs), motion analysis, traffic monitoring, speed estimation, modular architecture, IoT-enabled infrastructure, road safety enhancement.
Abstract
Forecasting Stock Prices using ARIMA algorithm
BAVANEESWAR. K, Mrs. MENAKA.P
DOI: 10.17148/IJIREEICE.2025.13353
Abstract: The stock prediction project presented here aims to develop an interactive application for analysing and forecasting stock prices using historical data. The project utilizes Python's Tkinter for a graphical user interface, enabling users to input National Stock Exchange (NSE) company symbols and fetch stock data from Yahoo Finance. The application retrieves one year of historical stock prices, including closing prices and trading volumes. The project further enhances analysis by incorporating moving averages—50day and 200-day—to provide trend insights. For predictive analytics, the system employs the ARIMA (Auto Regressive Integrated Moving Average) model, a well-established time- series forecasting technique. This model is trained on the stock’s closing prices and generates future price predictions for the next 30 days. The results are visually represented through Matplotlib, with historical prices, moving averages, trading volumes, and forecasted prices displayed on interactive charts. This project is particularly useful for investors, traders, and financial analysts seeking to understand stock trends and predict potential future movements. The intuitive interface allows users to seamlessly interact with stock data, view market trends, and make data-driven decisions. The integration of real-time data fetching, statistical modeling, and visualization makes this application a powerful tool for stock market analysis.
Abstract
STRESS DETECTON BASED ON FACIAL EXPRESSION
T. JAYASREE, DR. K. THENMOZHI
DOI: 10.17148/IJIREEICE.2025.13354
Abstract: Stress detection using facial expressions has become an important area of research in the field of human- computer interaction and mental health monitoring. This paper proposes a novel approach for identifying stress levels based on facial expression analysis. Stress is a common psychological condition that can negatively affect an individual's health and performance. Traditional methods of stress detection are often intrusive or rely on self-reporting, which can be inaccurate. By leveraging facial expression recognition techniques, this study aims to provide a non-invasive, real- time solution for assessing stress levels. The system utilizes machine learning algorithms to analyze facial features such as eye movement, brow furrowing, and mouth position to classify stress intensity. A dataset of labeled facial expressions corresponding to different stress levels was used to train the model. The results demonstrate the potential of using facial expression analysis as a reliable method for stress detection, with promising applications in healthcare, education, and workplace settings. Future work will focus on improving accuracy, real-time processing capabilities, and integration with other physiological indicators of stress.
Keywords: Stress Detection, Facial Expression Recognition, Emotion Recognition, Affective Computing Facial Feature Analysis ,Stress Classification, Emotion Classification , Mental Health Monitoring.
Keywords: Stress Detection, Facial Expression Recognition, Emotion Recognition, Affective Computing Facial Feature Analysis ,Stress Classification, Emotion Classification , Mental Health Monitoring.
Abstract
VOICE-TO-SIGN TRANSLATOR FOR EMPOWERING COMMUNICATION WITH DEAF AND MUTE
J.VARSHA, Dr. K BANUROOPA
DOI: 10.17148/IJIREEICE.2025.13355
Abstract: Access to information and interactions is severely restricted by communication obstacles between the hearing and the deaf or mute cultures. In order to solve this problem, a Python program called "Voice-to-Sign Translator" was created to convert spoken English into animated representations of Indian Sign Language. This project uses a user- friendly interface to empower deaf and mute persons by allowing for efficient communication in brief, predictable settings such as classrooms, airports, and customer service lines. By focussing on ISL, the system attempts to satisfy the unique needs of Indian users while also improving accessibility in regular interactions. The application uses Python's sophisticated speech recognition and computer graphics tools to dynamically convert spoken English into ISL signs. A 3D graphical representation of ISL gestures is displayed on the screen in real-time, allowing users to comprehend spoken instructions visually. Unlike traditional sign translation systems, this project emphasizes voice-to-sign conversion, addressing limited domains where brief, predictable communication is required. This approach makes the system ideal for organised environments, boosting efficiency and inclusion. This system integrates Python-based speech recognition APIs like Google Speech Recognition with advanced animation tools like Blender or PyOpenGL for 3D modelling. The technology links spoken words and phrases to their corresponding ISL gestures using a database to guarantee accurate and context-sensitive translations. Furthermore, the project prioritises usability and accessibility, with features designed to accommodate non-technical users.
Abstract
Car spare parts and service provider Platform
A. B. Bhawin, Mrs. A. Sathiya Priya
DOI: 10.17148/IJIREEICE.2025.13356
Abstract: The intention of the proposed project is to create an internet-based and mobile application that links consumers and auto spare parts merchants, providing a complete solution for selling both brand-new and used parts and streamlining the repair processes. Customers can find and buy components quickly because to the platform's advanced search filters, real-time inventory updates, and user-friendly interface. While integrated geolocation services locate local dealers and mechanics, dealers may display their items with thorough descriptions to guarantee exposure and transparency. Part compatibility is guaranteed by an intelligent recommendation system, and quality assurance is upheld by a review mechanism. The app is a one-stop shop for auto maintenance since it also has a mechanic booking function that lets users hire a professional to help with installation.
Keywords: Geolocation services, Maintenance, Dealers and mechanics, Auto spare parts
Keywords: Geolocation services, Maintenance, Dealers and mechanics, Auto spare parts
Abstract
GRAPHICAL PASSWORD IMAGE SEGMENTATION: A NOVEL APPROACH TO ENHANCED ONLINE SECURITY
OMPRAKASH T, Dr.R. PRABA
DOI: 10.17148/IJIREEICE.2025.13357
Abstract: Captcha technology with graphical password systems, which are also known as Captcha as Graphical Passwords (CaRP), the project "Graphical Password Image Segmentation" enhances security online. The project, designed using ASP.Net as the front end, Microsoft SQL Server as the back end, and Windows 8 as the platform, is made up of modules such as File Upload/Download, Graphical Password, Captcha in Authentication, Registration, and Key Generation (Cued Click Points). CaRP provides more secure password selection by solving the hotspot problem of the image in traditional graphical password schemes. By restricting unauthorised file downloads and uploads, providing secure file sharing between users, and restricting system access to only authorised users through image-based Captcha authentication, it provides greater security
Keywords: Graphical Password, Captcha as Graphical Password (CaRP), Cued Click Points, Secure Authentication, File Management.
Keywords: Graphical Password, Captcha as Graphical Password (CaRP), Cued Click Points, Secure Authentication, File Management.
Abstract
COLLEGE FORUMS WITH ALUMNI BASED ON CONTENT FILTERING
Vishwa.B, Mrs.A.Sathiya Priya
DOI: 10.17148/IJIREEICE.2025.13358
Abstract: College forums serve as essential platforms for communication, knowledge sharing, and networking among students and alumni. However, traditional forums often lack personalization, leading to irrelevant content recommendations and limited engagement. To address this issue, a content-based filtering approach can be implemented to enhance interactions within college forums by recommending relevant discussions, resources, and alumni connections based on user preferences and past activities. By utilizing natural language processing (NLP) and machine learning techniques, the system can analyze forum content, user interests, and alumni expertise to provide personalized recommendations. This ensures that students are connected with alumni who share similar academic or career interests, fostering mentorship opportunities and career guidance. The content-filtering approach improves the relevance of forum discussions, leading to increased user engagement and more meaningful interactions. Additionally, it creates an adaptive learning environment where students receive tailored insights and support from experienced alumni. Future enhancements may involve hybrid filtering techniques, integrating collaborative filtering to further refine recommendation accuracy. This work contributes to the development of intelligent, personalized college forums that strengthen alumni networks and promote continuous learning and professional growth.
Keywords: College forums, alumni network, content-based filtering, personalized recommendations, Natural Language Processing (NLP), machine learning, mentorship, career guidance, user engagement, adaptive learning.
Keywords: College forums, alumni network, content-based filtering, personalized recommendations, Natural Language Processing (NLP), machine learning, mentorship, career guidance, user engagement, adaptive learning.
Abstract
Complaint Registration App for E-Governance
Ms. S. Revathi, Dr. J. Savitha M.Sc., M.Phil., Ph.D.
DOI: 10.17148/IJIREEICE.2025.13359
Abstract: The "Complaint Registration App for e-governance" is a revolutionary computer application aimed at empowering citizens by making the easy registration and monitoring of complaints with government departments or private bodies a reality. By offering a friendly interface, the application makes it easy for users to provide vital information regarding their complaints, such as the type of complaint, the location, and relevant information or documentation. The application features a number of features designed to make complaint submission easier, enhance communication between people and the organization, and generally improve the user experience.Some of the key functions of the application are real-time reporting of status, automatic alerts, and a secure environment for exchanging confidential information. All these functions complement each other to ensure that people are well-informed about the status of their grievances, and this helps to instill transparency and confidence in the settlement process. The application also provides multilingual support for enabling a wide range of users.The application uses the latest technologies and frameworks like React, HTML, CSS, JavaScript, and server-side programming languages to build a smooth and interactive user experience. By combining these technologies, the application offers a strong and scalable solution that can be easily customized to suit the requirements of various organizations and jurisdictions.The "Complaint Registration App for e- governance" is conceived to enhance the effectiveness and efficiency of the complaint filing process to ensure that the grievances raised by people are settled in a timely and thorough manner. Through encouraging a culture of responsiveness and accountability, the app seeks to reduce the gap between people and institutions, eventually leading to improved governance and enhanced delivery of public services.
Keywords: Transparency, Efficiency, Accountability, User-friendly, Real-time updates
Keywords: Transparency, Efficiency, Accountability, User-friendly, Real-time updates
Abstract
CNN-BASED IMAGE DETECTOR FOR PLANT LEAF DISEASES CLASSIFICATION
RATHYA.N, Dr. K. THENMOZHI
DOI: 10.17148/IJIREEICE.2025.13360
Abstract: Identifying diseases from images of plant leaves is one of the most important research areas in precision agriculture. The aim of this paper is to propose an image detector embed ding a resource constrained convolutional neural network (CNN) implemented in a low cost, low power platform, named Open MV Cam H7 Plus, to perform a real- time classification of plant disease. The CNN network so obtained has been trained on two specific data sets for plant diseases detection, the ESCA-dataset and the Plant Village-augmented dataset, and implemented in a low-power, low-cost Python programmable machine vision camera for real-time image acquisition and classification, equipped with a LCD display showing to the user the classification response in real-time. Experimental results show that this CNN based image detector can be effectively implemented on the chosen constrained-resource system, achieving an accuracy of about 98.10%/95.24% with a very low memory cost (718. 961 KB/735.727 KB) and inference time (122.969ms/125.630ms) tested on board for the ESCA and the Plant Village-augmented datasets respectively, allowing the design of a portable embedded system for plant leaf diseases classification.
Keywords: Image detector Esca disease convolutional neural network embedded systems plant diseases recognition
Keywords: Image detector Esca disease convolutional neural network embedded systems plant diseases recognition
Abstract
TURFLINK-THE SPORTS FACILITY BOOKING PLATFORM
Ashok Kumar S, Dr. R. Praba
DOI: 10.17148/IJIREEICE.2025.13361
Abstract: In today's digital age, the process of searching and booking a sports facility is most often a hassle, marked by insufficient space, complex scheduling, and the added hassle of managing food and drinks on one's own. “TurfLink – The Sports Booking Platform” seeks to make this process simpler by offering a single online destination for booking sports facilities while offering the convenience of pre-ordering food and drinks. Whether one wishes to play football, cricket, badminton, tennis, or basketball, TurfLink allows users to search for available venues, confirm real-time slot availability, and book instant bookings with secure payment facilities. The uniqueness of TurfLink is its “built-in snack ordering feature”, which enables players and spectators to enjoy their favorite foods and drinks easily and quickly without the hassles of looking for vendors or waiting in long queues. Users can pre-order refreshments through a few clicks, thus optimizing the overall enjoyment and convenience of their sporting experience. The website also has a user-friendly dashboard where players can book, view past bookings, and receive reminders for future games, deals, and promotions. For venue operators, TurfLink offers a simple-to-use management system to optimize booking time slots, boost revenue, and enhance customer engagement. In addition, the platform applies “AI-driven recommendations” to suggest the best time slots and snack pairings based on users' preferences and thus customize the entire experience. Multiple payment options, such as UPI, digital wallets, and credit/debit cards, facilitate convenient and secure payments. By combining “sports facility booking and food ordering”, TurfLink provides an end-to-end solution that achieves maximum convenience, operational effectiveness, and customer satisfaction.
Keywords: Sports facility booking, Turf reservation system, Sports venue management, Tournament registration platform, Digital booking platform, Facility availability tracking, Location-based turf search, User-friendly booking interface, Snacks ordering system
Keywords: Sports facility booking, Turf reservation system, Sports venue management, Tournament registration platform, Digital booking platform, Facility availability tracking, Location-based turf search, User-friendly booking interface, Snacks ordering system
Abstract
APP SECURITY ANALYSER: AI BASED FRAUD DETECTION USING SENTIMENT INSIGHT
SIVASAMY P, DR. J. SAVITHA
DOI: 10.17148/IJIREEICE.2025.13362
Abstract: Mobile App store ranking fraud is given the meaning that it refers to deceptive or malicious acts that perform the function of promoting the Apps in the popular list. Really, it grows more and more usual for developers of Apps to use dishonest actions, such as overstating sales of their Apps or providing untrue App ratings, to commit ranking fraud. While the importance of ranking fraud prevention has been comprehensively understood, research and knowledge on this front are limited. In this regard, in this paper, we discuss a thorough overview of ranking fraud and propose a ranking fraud detection system for mobile Apps. Specifically, we first propose to accurately identify the ranking fraud by mining active time, i.e., leading sessions, of mobile Apps. Such trailblazing sessions may be used for local anomaly identification instead of global anomaly of App rankings. Besides, we investigate three evidences, i.e., ranking based evidences, rating based evidences and review based evidences, by explaining Apps' ranking, rating and review behaviors through statistical hypotheses tests.
Abstract
Analyzing, controlling, and dynamically modeling a standalone wind-diesel power system using a GA-PID controller
Dr. M Sankaraiah, Dr. Sd Munvar Ali, Dr. P Ramesh
DOI: 10.17148/IJIREEICE.2025.13363
Abstract: This work focuses on the modeling, control, and dynamic analysis of a small, isolated electric power system consisting of a diesel engine and a wind turbine generator. A time-domain dynamic study of an electric power system utilizing simplified models of its constituent parts takes into account the wind turbine's pitch controller and the diesel engine's speed regulator. Wind gusts, rapid ramp changes, and random noise components comprise the wind disturbance model. The diesel generator supplies the additional power required by the load, while the wind turbine generator is always operated at its rated capacity. Two control schemes—proportional-integral (PI) and proportional-integral-derivative (PID) controllers—are employed in this work to improve the wind-diesel power system's dynamic performance in the face of load and wind disturbances. The diesel generator provides the extra power needed by the load, while the wind turbine generator is always run at its rated power. Two control schemes—proportional-integral (PI) and proportional- integral-derivative (PID) controllers—are employed in this work to improve the wind-diesel power system's dynamic performance in the face of load and wind disturbances. Genetic algorithms (GA) and other optimization approaches are used to optimize the gain parameters of PI and PID controllers. The results of the simulation are shown, and the dynamic performance of the wind-diesel power system is compared for various PI and PID controller optimum gain settings that were determined using GA.
Keywords: PID controller, Genetic Algorithm based PID (GAPID) controller,
Keywords: PID controller, Genetic Algorithm based PID (GAPID) controller,
Abstract
Design and Implementation of FPGA controlled Nine Level Inverter
Dr. Sd Munvar Ali, Dr. P Ramesh, M Sankaraiah
DOI: 10.17148/IJIREEICE.2025.13364
Abstract: In this paper a nine-level staggered multi level inverter (MLI) by FPGA controller is presented. This inverter produces nine levels of AC output voltages with the effective gate signal design. The proposed inverter needs a single DC voltage supply with chain connection of four capacitors, five diodes, eight switches to synthesize output voltage levels and H-bridge cell. With single DC voltage source the present inverter eliminates the impartial allocation of DC voltage sources and switches. The switching losses and voltage stresses in the present converter are reduced. The total harmonic distortion (THD) in the output voltage is also less when compared to conventional topologies. The proposed work is first simulated in MATLAB/Simulink environment and then implemented using FPGA controller with VHDL interface.
Keywords: Multilevel inverter; voltage balance; AC output voltage; Total harmonic distortion (THD); FPGA controller.
Keywords: Multilevel inverter; voltage balance; AC output voltage; Total harmonic distortion (THD); FPGA controller.
Abstract
A Novel Control Method for Enhancing Stability of Interconnected Three Areas System
V.Pardha Saradhi, K.sudherr, Dr.I.prabhakar reddy
DOI: 10.17148/IJIREEICE.2025.13365
Abstract: In modern power systems, maintaining stability across interconnected areas is critical, especially with the growing complexity of the grid. This paper presents a Genetic Algorithm (GA)-based Proportional-Integral-Derivative (PID) controller design for enhancing the dynamic stability of a three-area power system. Traditional PID controllers often struggle with optimal tuning due to the non-linear and dynamic nature of power systems. In this study, a Genetic Algorithm is employed to optimize the PID parameters by minimizing a performance index, such as the Integral of Time- weighted Absolute Error (ITAE), thereby ensuring faster and more robust frequency and tie-line power oscillation damping. Simulation results demonstrate that the GA-tuned PID controller significantly improves the dynamic response compared to conventional tuning methods, providing better system resilience to disturbances and load variations. The proposed approach offers a promising solution for achieving reliable and efficient automatic generation control (AGC) in multi-area power systems.
Keywords: PID controller, Genetic Algorithm based PID (GAPID) controller, Automatic Generation Control (AGC)
Keywords: PID controller, Genetic Algorithm based PID (GAPID) controller, Automatic Generation Control (AGC)
Abstract
Impact Of Electrical Vehicle Charging Station And Fault Ride Through Capability Under Critical Voltage Conditions
S D S Bhagyamma, J Charishma, S Suresh Reddy
DOI: 10.17148/IJIREEICE.2025.13366
Abstract: The electric vehicle (EV) charging system requires a high-quality power supply to function correctly. The purpose of this study is to look at the impacts of voltage disruption on EV batteries and charging systems, as voltage quality is one of the primary issues in the distribution grid. To increase voltage quality, we also implemented a fault ride through capability (FRTC). The charging system consists of a DC-DC converter and a three-phase controlled rectifier. Lithium-ion batteries are used to simulate EV battery packs. The FRTC system is designed to improve voltage quality by utilizing a dynamic voltage restorer. It protects the charging system and EV batteries against dangerously excessive voltage sag levels. The performance of the proposed EV charging station (EVCS) was evaluated at voltage sag levels of 30%. Matlab/Simulink software was used to analyse the simulation data.
Keywords: Fault Ride Through Capability (FRTC), Electric Vehicle (EV) ,EV Charging Station (EVCS)
Keywords: Fault Ride Through Capability (FRTC), Electric Vehicle (EV) ,EV Charging Station (EVCS)
Abstract
HARMONIC REDUCTION OF POWER QUALITY WITH A FUZZY LOGIC BASED SHUNT ACTIVE POWER FILTER
Dr. S Suresh Reddy, S.D.S Bhagyamma, J Charishma
DOI: 10.17148/IJIREEICE.2025.13367
Abstract: In order to support the superiority of one current control strategy over the other, this paper provides a detailed performance analysis of SAPF under two current control strategies: synchronous frame reference theory (d-q) and instantaneous active and reactive power theory (p-q). In both approaches, a reference current is produced for the filter that corrects the power system's reactive power or harmonic current component. This study describes a current controller called a harmonic current controller, which helps to eliminate harmonics by providing the IGBT inverter with a corrected gating sequence. In this study, traditional PI controllers and fuzzy logic controllers are employed to generate pulses properly.
Keywords: Shunt Active Power Filter (SAPF), IGBT, Fuzzy Logic Controller (FLC)
Keywords: Shunt Active Power Filter (SAPF), IGBT, Fuzzy Logic Controller (FLC)
Abstract
Power management based on ANFIS controllers in autonomous microgrids
M Sreenivasulu, R Ramprasad, T Mabu subhani
DOI: 10.17148/IJIREEICE.2025.13368
Abstract: In order to manage reactive power in islanded microgrids, this research suggests various power management strategies, including proportional and equal power sharing in droop control. The synchronous generators were the first to use the droop control. Additionally, this project converts the voltage source converter to droop control. Fuel cell and wind power generation systems are examples of dispersed generation systems. Only the fuel cell's rated active power may be taken into consideration in this article.
The ANFIS controller is proposed in this study, and its efficacy is contrasted with that of the PI controller.
Keywords: Adaptive Neuro Fuzzy System (ANFIS), Proportional Integral controller (PI Controller), Voltage Source Converter (VSC).
The ANFIS controller is proposed in this study, and its efficacy is contrasted with that of the PI controller.
Keywords: Adaptive Neuro Fuzzy System (ANFIS), Proportional Integral controller (PI Controller), Voltage Source Converter (VSC).
Abstract
Dynamic Stability Enhancement using PSS and UPFC
K V Thulasiram, Dr. N Usha, P Dhana Selvi
DOI: 10.17148/IJIREEICE.2025.13369
Abstract: This research proposes a new PSO-based PSS for the UPFC to dampen power system low frequency oscillations. A power system stabilizer is developed for UPFC to efficiently damp the oscillations of the power system. The parameters of PSS are tuned using the PSO algorithm. The effectiveness of the proposed control technique is tested under various fault scenarios and compared to the GA-based PSS to demonstrate its robust performance using time simulation studies and certain performance indices.
Keywords: UPFC, GA, PSO, FACTS devices, Power System Stability.
Keywords: UPFC, GA, PSO, FACTS devices, Power System Stability.
Abstract
Hybrid Renewable Energy System Control for Maximum Power Extraction and Output Voltage Regulation by Using Fuzzy logic Controller
G Subba Reddy, V Anjaneyulu, N Rammohan
DOI: 10.17148/IJIREEICE.2025.13370
Abstract: The purpose of this paper is to investigate novel control strategies for hybrid PV/wind control systems. The paper's other result is a description of the attractive controller for the proposed hybrid system. When designing the control process for control systems with limitless energy sources, two primary objectives must be accomplished. Removing the most control from renewable energy sources, such as wind and photovoltaics, is a critical issue. A hybrid double-input (PV/Wind) control system was constructed, simulated in MATLAB, and novel control strategies were assessed in this study. PV panels, wind energy conversion systems (WEC), and a DC/DC converter comprise the proposed control system. The wind control plant model consists of a wind turbine, a PMSG generator, and a rectifier that transfers DC electrical power. PV modules can be joined in a variety of ways to form solar arrays. This page focuses on the replication of PV cells, modules, and clusters. The study concludes with an examination of the execution of the suggested control mechanism.
Keywords: wind energy conversion systems (WEC), hybrid double-input (PV/Wind), Fuzzy logic Controller
Keywords: wind energy conversion systems (WEC), hybrid double-input (PV/Wind), Fuzzy logic Controller
Abstract
Relationship of Flexibility and Injuries in Sports: A Review
Jai Bhagwan Singh Goun
DOI: 10.17148/IJIREEICE.2025.13371
Abstract: Flexibility, defined as the range of motion (ROM) available at a joint or group of joints, plays a crucial role in athletic performance and injury prevention. It is often assumed that enhanced flexibility can reduce the risk of musculoskeletal injuries by allowing joints to move freely without mechanical restriction. However, scientific findings regarding this relationship remain inconsistent. This review explores the relationship between flexibility and sports- related injuries across various athletic populations.
Studies suggest that both insufficient and excessive flexibility can predispose athletes to injury. Limited flexibility may lead to compensatory movement patterns, resulting in increased joint stress, particularly in high-impact and repetitive motion sports such as football, basketball, gymnastics, and running. Conversely, hypermobility or joint laxity can cause joint instability, making athletes more vulnerable to sprains, strains, and dislocations. Static stretching, once widely promoted as a preventive measure, has shown mixed results in its effectiveness at reducing injury rates.
This review synthesizes findings from observational studies, randomized controlled trials, and meta-analyses to evaluate how flexibility influences injury incidence, considering variables such as sport type, gender, age, and level of competition. Key areas explored include the role of dynamic vs. static flexibility, muscle imbalance, flexibility asymmetry, and sport-specific ROM demands.
Results indicate that optimal (but not excessive) flexibility, tailored to the demands of the sport, is more protective than generalized stretching routines. Dynamic stretching and active ROM exercises appear more effective in injury prevention than passive static stretches alone. Additionally, individualized flexibility assessments may help identify athletes at risk due to either hypo- or hypermobility.
Understanding the complex relationship between flexibility and injury is essential for designing evidence-based warm- up routines, rehabilitation protocols, and sport-specific flexibility programs. This review highlights the importance of balance between mobility and stability, emphasizing flexibility as one of many factors influencing sports injury risk.
Keywords: Flexibility, Sports injuries, Range of motion, Static stretching, Dynamic stretching, Hypermobility, Injury prevention
Studies suggest that both insufficient and excessive flexibility can predispose athletes to injury. Limited flexibility may lead to compensatory movement patterns, resulting in increased joint stress, particularly in high-impact and repetitive motion sports such as football, basketball, gymnastics, and running. Conversely, hypermobility or joint laxity can cause joint instability, making athletes more vulnerable to sprains, strains, and dislocations. Static stretching, once widely promoted as a preventive measure, has shown mixed results in its effectiveness at reducing injury rates.
This review synthesizes findings from observational studies, randomized controlled trials, and meta-analyses to evaluate how flexibility influences injury incidence, considering variables such as sport type, gender, age, and level of competition. Key areas explored include the role of dynamic vs. static flexibility, muscle imbalance, flexibility asymmetry, and sport-specific ROM demands.
Results indicate that optimal (but not excessive) flexibility, tailored to the demands of the sport, is more protective than generalized stretching routines. Dynamic stretching and active ROM exercises appear more effective in injury prevention than passive static stretches alone. Additionally, individualized flexibility assessments may help identify athletes at risk due to either hypo- or hypermobility.
Understanding the complex relationship between flexibility and injury is essential for designing evidence-based warm- up routines, rehabilitation protocols, and sport-specific flexibility programs. This review highlights the importance of balance between mobility and stability, emphasizing flexibility as one of many factors influencing sports injury risk.
Keywords: Flexibility, Sports injuries, Range of motion, Static stretching, Dynamic stretching, Hypermobility, Injury prevention
Abstract
Design and Implementation of a High-Speed Charging Architecture for Intelligent Solar-Powered Battery Charging and Swapping Stations
Onyeyili T.I, Oranugo C.O, Ugwuanyi Gilbert
DOI: 10.17148/IJIREEICE.2025.13372
Abstract: The rapid expansion of electric vehicle (EV) adoption necessitates advanced, user-oriented charging infrastructures capable of accommodating variable daily demand. Conventional plug-in charging methods often result in prolonged vehicle downtime, prompting the exploration of battery-swapping stations as a practical alternative. This study presents the design and implementation of a high-speed solar charging architecture tailored for smart battery-swap stations. The system integrates a fast Maximum Power Point Tracking (MPPT) DC-DC solar charge controller engineered to recharge lithium-ion battery packs from 0 % to 100 % within approximately 2–3 hours. Key design objectives include maximizing charging efficiency, prolonging battery lifespan, and incorporating intelligent thermal- management strategies. Performance optimization is achieved through an advanced control algorithm executed on an ESP32 microcontroller, leveraging its high-frequency processing capability, dedicated analog-to-digital conversion for precise switching control, and Wi-Fi connectivity for real-time parameter adjustment. Experimental validation confirms the enhanced reliability and efficiency of the proposed fast-charging system, positioning it as a robust solution for next- generation smart solar charge/swap infrastructures.
Keywords: Fast Charging · Smart Solar Station · Battery Swapping · Power Electronics · Renewable Energy Integration
Keywords: Fast Charging · Smart Solar Station · Battery Swapping · Power Electronics · Renewable Energy Integration